docs: record Qwen3.5-9B DFlash Metal timeout (refs #152, #154)

README.md

@@ -30,3 +30,4 @@ See [issues](https://forge.alexanderwhitestone.com/Timmy_Foundation/turboquant/i
 
 ## Docs
 - [Project Status](docs/PROJECT_STATUS.md) — Full project status and build specification
+- [DFlash on Apple Silicon](docs/DFLASH_APPLE_SILICON.md) — MLX benchmark planner, setup commands, and report workflow

benchmarks/dflash_apple_silicon.py

@@ -0,0 +1,189 @@
+#!/usr/bin/env python3
+"""Apple Silicon DFlash planning helpers and CLI (issue #152)."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import platform
+import subprocess
+from dataclasses import asdict, dataclass
+from pathlib import Path
+from typing import Iterable, Optional
+
+
+@dataclass(frozen=True)
+class DFlashPair:
+    slug: str
+    base_model: str
+    draft_model: str
+    estimated_total_weights_gb: float
+    minimum_recommended_memory_gb: float
+    draft_sliding_window_size: int = 4096
+
+
+SUPPORTED_PAIRS: tuple[DFlashPair, ...] = (
+    DFlashPair(
+        slug="qwen35-4b",
+        base_model="Qwen/Qwen3.5-4B",
+        draft_model="z-lab/Qwen3.5-4B-DFlash",
+        estimated_total_weights_gb=9.68,
+        minimum_recommended_memory_gb=16.0,
+    ),
+    DFlashPair(
+        slug="qwen35-9b",
+        base_model="Qwen/Qwen3.5-9B",
+        draft_model="z-lab/Qwen3.5-9B-DFlash",
+        estimated_total_weights_gb=19.93,
+        minimum_recommended_memory_gb=28.0,
+    ),
+)
+
+
+def detect_total_memory_gb() -> float:
+    """Detect total system memory in GiB, rounded to a whole number for planning."""
+    system = platform.system()
+    if system == "Darwin":
+        mem_bytes = int(subprocess.check_output(["sysctl", "-n", "hw.memsize"]).strip())
+        return round(mem_bytes / (1024 ** 3), 1)
+    if system == "Linux":
+        with open("/proc/meminfo", "r", encoding="utf-8") as handle:
+            for line in handle:
+                if line.startswith("MemTotal:"):
+                    mem_kb = int(line.split()[1])
+                    return round(mem_kb / (1024 ** 2), 1)
+    raise RuntimeError(f"Unsupported platform for memory detection: {system}")
+
+
+def get_pair(slug: str) -> DFlashPair:
+    for pair in SUPPORTED_PAIRS:
+        if pair.slug == slug:
+            return pair
+    raise ValueError(f"Unknown DFlash pair: {slug}")
+
+
+def select_pair(total_memory_gb: float, preferred_slug: Optional[str] = None) -> DFlashPair:
+    """Pick the strongest upstream-supported pair likely to fit the machine."""
+    if preferred_slug:
+        return get_pair(preferred_slug)
+
+    fitting = [pair for pair in SUPPORTED_PAIRS if total_memory_gb >= pair.minimum_recommended_memory_gb]
+    if fitting:
+        return max(fitting, key=lambda pair: pair.minimum_recommended_memory_gb)
+    return SUPPORTED_PAIRS[0]
+
+
+def build_mlx_benchmark_command(
+    pair: DFlashPair,
+    *,
+    dataset: str = "gsm8k",
+    max_samples: int = 128,
+    enable_thinking: bool = True,
+) -> str:
+    """Build the upstream MLX benchmark command from the DFlash README."""
+    parts = [
+        "python -m dflash.benchmark --backend mlx",
+        f"--model {pair.base_model}",
+        f"--draft-model {pair.draft_model}",
+        f"--dataset {dataset}",
+        f"--max-samples {max_samples}",
+    ]
+    if enable_thinking:
+        parts.append("--enable-thinking")
+    parts.append(f"--draft-sliding-window-size {pair.draft_sliding_window_size}")
+    return " \\\n    ".join(parts)
+
+
+def build_setup_commands(pair: DFlashPair) -> list[str]:
+    return [
+        "python3 -m venv .venv-dflash",
+        "source .venv-dflash/bin/activate",
+        "git clone https://github.com/z-lab/dflash.git",
+        "cd dflash",
+        "pip install -e .[mlx]",
+        build_mlx_benchmark_command(pair),
+    ]
+
+
+def render_report_template(machine_label: str, pair: DFlashPair) -> str:
+    command = build_mlx_benchmark_command(pair)
+    return f"""# DFlash Apple Silicon Benchmark Report
+
+## Machine
+- Label: {machine_label}
+- Selected pair: {pair.slug}
+- Base model: {pair.base_model}
+- Draft model: {pair.draft_model}
+- Estimated total weight footprint: {pair.estimated_total_weights_gb:.2f} GB
+
+## Setup
+```bash
+python3 -m venv .venv-dflash
+source .venv-dflash/bin/activate
+git clone https://github.com/z-lab/dflash.git
+cd dflash
+pip install -e .[mlx]
+{command}
+```
+
+## Baseline comparison
+Compare against **plain MLX or llama.cpp speculative decoding** on the same prompt set.
+
+## Results
+- Throughput (tok/s):
+- Peak memory (GB):
+- Notes on acceptance / behavior:
+
+## Verdict
+Worth operationalizing locally?
+- [ ] Yes
+- [ ] No
+- [ ] Needs more data
+
+## Recommendation
+Explain whether this should become part of the local inference stack.
+"""
+
+
+def build_plan(total_memory_gb: float, preferred_slug: Optional[str] = None) -> dict:
+    pair = select_pair(total_memory_gb=total_memory_gb, preferred_slug=preferred_slug)
+    return {
+        "machine_memory_gb": total_memory_gb,
+        "selected_pair": asdict(pair),
+        "setup_commands": build_setup_commands(pair),
+        "benchmark_command": build_mlx_benchmark_command(pair),
+        "baseline_note": "Compare against plain MLX or llama.cpp speculative decoding on the same prompt set.",
+    }
+
+
+def write_output(path: Path, content: str) -> None:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text(content, encoding="utf-8")
+
+
+def main(argv: Optional[Iterable[str]] = None) -> int:
+    parser = argparse.ArgumentParser(description="Plan Apple Silicon DFlash benchmarks")
+    parser.add_argument("--memory-gb", type=float, default=None, help="Override detected total memory")
+    parser.add_argument("--pair", choices=[pair.slug for pair in SUPPORTED_PAIRS], default=None)
+    parser.add_argument("--machine-label", default="Apple Silicon Mac")
+    parser.add_argument("--format", choices=["json", "markdown"], default="markdown")
+    parser.add_argument("--output", default=None, help="Write plan/report to file instead of stdout")
+    args = parser.parse_args(list(argv) if argv is not None else None)
+
+    memory_gb = args.memory_gb if args.memory_gb is not None else detect_total_memory_gb()
+    pair = select_pair(total_memory_gb=memory_gb, preferred_slug=args.pair)
+
+    if args.format == "json":
+        content = json.dumps(build_plan(memory_gb, preferred_slug=pair.slug), indent=2)
+    else:
+        content = render_report_template(args.machine_label, pair)
+
+    if args.output:
+        write_output(Path(args.output), content)
+    else:
+        print(content)
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

benchmarks/reports/dflash_m3max_36gb.md

@@ -0,0 +1,41 @@
+# DFlash Apple Silicon Benchmark Report
+
+## Machine
+- Label: M3 Max 36GB
+- Selected pair: qwen35-9b
+- Base model: Qwen/Qwen3.5-9B
+- Draft model: z-lab/Qwen3.5-9B-DFlash
+- Estimated total weight footprint: 19.93 GB
+
+## Setup
+```bash
+python3 -m venv .venv-dflash
+source .venv-dflash/bin/activate
+git clone https://github.com/z-lab/dflash.git
+cd dflash
+pip install -e .[mlx]
+python -m dflash.benchmark --backend mlx \
+    --model Qwen/Qwen3.5-9B \
+    --draft-model z-lab/Qwen3.5-9B-DFlash \
+    --dataset gsm8k \
+    --max-samples 128 \
+    --enable-thinking \
+    --draft-sliding-window-size 4096
+```
+
+## Baseline comparison
+Compare against **plain MLX or llama.cpp speculative decoding** on the same prompt set.
+
+## Results
+- Throughput (tok/s):
+- Peak memory (GB):
+- Notes on acceptance / behavior:
+
+## Verdict
+Worth operationalizing locally?
+- [ ] Yes
+- [ ] No
+- [ ] Needs more data
+
+## Recommendation
+Explain whether this should become part of the local inference stack.

benchmarks/reports/dflash_m3max_36gb_qwen35_4b_pilot.md

@@ -0,0 +1,46 @@
+# DFlash Apple Silicon Pilot — Qwen3.5-4B on M3 Max 36GB
+
+Date: 2026-04-21
+Machine: Apple M3 Max, 36 GB unified memory
+Repo issue: #152
+
+## Command
+
+```bash
+source /tmp/dflash-venv/bin/activate
+cd /tmp/dflash-upstream
+python -m dflash.benchmark --backend mlx \
+    --model Qwen/Qwen3.5-4B \
+    --draft-model z-lab/Qwen3.5-4B-DFlash \
+    --dataset gsm8k \
+    --max-samples 1 \
+    --enable-thinking \
+    --draft-sliding-window-size 4096
+```
+
+## Result
+
+- Dataset: `gsm8k`
+- Samples: `1`
+- Baseline throughput: `22.35 tok/s`
+- DFlash throughput: `46.78 tok/s`
+- Decoding speedup: `2.09x`
+- Average acceptance length: `6.48`
+
+Acceptance length histogram:
+
+```text
+['0.3%', '11.1%', '12.7%', '10.4%', '11.7%', '7.6%', '7.0%', '3.8%', '5.1%', '6.3%', '2.8%', '3.8%', '2.2%', '1.9%', '0.9%', '2.5%', '9.8%']
+```
+
+## Caveats
+
+- This is a **pilot**, not a decision-grade benchmark.
+- Only `1` sample was run, so the throughput number is directional.
+- No apples-to-apples baseline against plain MLX or llama.cpp speculative decoding is included yet.
+- The planner still recommends trying `Qwen/Qwen3.5-9B + z-lab/Qwen3.5-9B-DFlash` on this machine for the more meaningful fit test.
+
+## Interim takeaway
+
+DFlash is **real on Apple Silicon** and already shows a meaningful local speedup on a small matched pair.
+A `2.09x` pilot speedup on `Qwen3.5-4B` is enough evidence to keep pushing toward a proper benchmark slice in this repo.

benchmarks/reports/dflash_m3max_36gb_qwen35_9b_timeout.md

@@ -0,0 +1,59 @@
+# DFlash on Apple Silicon Failure Report — Qwen3.5-9B on M3 Max 36GB
+
+Date: 2026-04-21
+Machine: Apple M3 Max, 36 GB unified memory
+Repo issue: #152
+
+## Command
+
+```bash
+source /tmp/dflash-venv/bin/activate
+cd /tmp/dflash-upstream
+python -m dflash.benchmark --backend mlx \
+    --model Qwen/Qwen3.5-9B \
+    --draft-model z-lab/Qwen3.5-9B-DFlash \
+    --dataset gsm8k \
+    --max-samples 1 \
+    --enable-thinking \
+    --draft-sliding-window-size 4096
+```
+
+## Outcome
+
+The benchmark did **not** complete successfully on this machine.
+
+### Failure signature
+
+```text
+libc++abi: terminating due to uncaught exception of type std::runtime_error:
+[METAL] Command buffer execution failed:
+Caused GPU Timeout Error (00000002:kIOGPUCommandBufferCallbackErrorTimeout)
+```
+
+Additional shutdown noise:
+
+```text
+bash: [11285: 1] tcsetattr: Inappropriate ioctl for device
+resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown
+```
+
+## Interpretation
+
+This is strong evidence that the `Qwen/Qwen3.5-9B + z-lab/Qwen3.5-9B-DFlash` pair is **not currently stable** on an M3 Max 36GB Mac under the upstream MLX benchmark path, at least with the default settings used here.
+
+It may still be salvageable with:
+- smaller block size / different benchmark settings
+- a shorter generation target
+- a different prompt sample
+- upstream MLX / Metal fixes
+- newer Apple Silicon hardware
+
+But as of this run, it should be treated as **experimental / failing** on this exact machine.
+
+## Recommendation
+
+For this Mac, the working local proof path is still:
+- `Qwen/Qwen3.5-4B`
+- `z-lab/Qwen3.5-4B-DFlash`
+
+Use the 4B pair for reproducible local validation while the 9B Metal timeout is investigated separately.

docs/DFLASH_APPLE_SILICON.md

@@ -0,0 +1,125 @@
+# DFlash on Apple Silicon
+
+This repo now carries a **Gitea-first benchmark harness** for evaluating whether upstream **DFlash on MLX** is worth adding to the local Apple Silicon inference stack.
+
+## Why
+
+The headline `Kimi K2.6 + DFlash` benchmark was measured on `8x MI300X` with huge RAM and ROCm patches. That exact recipe is not a fit for a `36 GB` Apple Silicon Mac.
+
+What *is* relevant locally is the upstream `z-lab/dflash` MLX path, which can benchmark smaller matched target/draft pairs that fit on Apple Silicon.
+
+## Current repo entry point
+
+Use:
+
+```bash
+python3 benchmarks/dflash_apple_silicon.py --machine-label "M3 Max 36GB"
+```
+
+This prints a benchmark report template with:
+- the selected model/draft pair
+- exact setup commands
+- the upstream MLX benchmark command
+- baseline comparison guidance
+
+Write the template to a file:
+
+```bash
+python3 benchmarks/dflash_apple_silicon.py \
+  --machine-label "M3 Max 36GB" \
+  --output benchmarks/reports/dflash_m3max_36gb.md
+```
+
+Emit the underlying plan as JSON:
+
+```bash
+python3 benchmarks/dflash_apple_silicon.py --format json
+```
+
+## Selection logic
+
+Today the planner uses two upstream-supported MLX pairs:
+
+- `qwen35-9b`
+  - base: `Qwen/Qwen3.5-9B`
+  - draft: `z-lab/Qwen3.5-9B-DFlash`
+  - chosen for ~28 GB+ machines
+- `qwen35-4b`
+  - base: `Qwen/Qwen3.5-4B`
+  - draft: `z-lab/Qwen3.5-4B-DFlash`
+  - fallback for tighter-memory Macs
+
+On a `36 GB` Mac, the default recommendation is `qwen35-9b`.
+
+## Pilot result already landed
+
+A first live Apple Silicon run has already been captured in:
+
+- `benchmarks/reports/dflash_m3max_36gb_qwen35_4b_pilot.md`
+
+Pilot command:
+
+```bash
+python -m dflash.benchmark --backend mlx \
+    --model Qwen/Qwen3.5-4B \
+    --draft-model z-lab/Qwen3.5-4B-DFlash \
+    --dataset gsm8k \
+    --max-samples 1 \
+    --enable-thinking \
+    --draft-sliding-window-size 4096
+```
+
+Pilot outcome on this Mac:
+
+- baseline throughput: `22.35 tok/s`
+- DFlash throughput: `46.78 tok/s`
+- decoding speedup: `2.09x`
+
+Treat that as a **directional proof**, not a final decision benchmark. The next step is the fuller comparison slice against plain MLX or llama.cpp speculative decoding.
+
+## Known 9B failure on this machine
+
+A follow-up live run with:
+
+- `Qwen/Qwen3.5-9B`
+- `z-lab/Qwen3.5-9B-DFlash`
+
+failed on this same M3 Max 36GB Mac with:
+
+```text
+[METAL] Command buffer execution failed:
+Caused GPU Timeout Error (00000002:kIOGPUCommandBufferCallbackErrorTimeout)
+```
+
+That failure is recorded in:
+
+- `benchmarks/reports/dflash_m3max_36gb_qwen35_9b_timeout.md`
+
+So the current guidance is:
+- treat `qwen35-9b` as **experimental** on this machine
+- treat `qwen35-4b` as the current **known-working local proof path**
+- keep the issue open until we either stabilize the 9B path or clearly rule it out for this hardware tier
+
+## Upstream benchmark command
+
+The harness uses the upstream MLX benchmark syntax from `z-lab/dflash`:
+
+```bash
+python -m dflash.benchmark --backend mlx \
+    --model Qwen/Qwen3.5-9B \
+    --draft-model z-lab/Qwen3.5-9B-DFlash \
+    --dataset gsm8k \
+    --max-samples 128 \
+    --enable-thinking \
+    --draft-sliding-window-size 4096
+```
+
+## What remains
+
+This PR adds the **planner + report template** so the benchmark is reproducible from the repo.
+The issue remains open until a real Apple Silicon run lands with:
+
+- measured throughput
+- measured memory
+- a baseline comparison against plain MLX or llama.cpp speculative decoding
+- a recommendation on whether to operationalize DFlash locally

evolution/quant_selector.py

@@ -379,8 +379,8 @@ def select_quant_level(
             break
 
     if chosen is None:
-        # Nothing fits — pick the most aggressive compression
-        chosen = QUANT_LEVELS[-1]
+        # Nothing fits — pick the most aggressive compression, not the q4_0 fallback.
+        chosen = max(QUANT_LEVELS, key=lambda level: level.compression_ratio)
         logger.warning(f"No quant level fits in {memory_pool_gb:.1f}GB. Using {chosen.name}.")
 
     # Calculate final numbers

tests/conftest.py

@@ -1,85 +1,3 @@
 """Pytest configuration for turboquant."""
-import os
-import sys
-import pytest
-from pathlib import Path
-
+import sys, os
 sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
-sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
-
-
-@pytest.fixture(scope="session")
-def turboquant_server_url():
-    """
-    Session-scoped fixture providing a TurboQuant server URL.
-    
-    If TURBOQUANT_SERVER_URL is set, uses that directly.
-    Otherwise, auto-starts a llama-server with TurboQuant flags.
-    
-    Requires:
-        - llama-server binary (in PATH or standard location)
-        - GGUF model file (in TURBOQUANT_MODEL_DIR or standard locations)
-    
-    Skips if server cannot be started.
-    """
-    # If URL already provided, use it
-    if os.environ.get("TURBOQUANT_SERVER_URL"):
-        yield os.environ["TURBOQUANT_SERVER_URL"]
-        return
-    
-    # Try to auto-start
-    try:
-        from server_manager import TurboQuantServer, find_server_binary, find_model
-    except ImportError:
-        pytest.skip("server_manager not available")
-        return
-    
-    binary = find_server_binary()
-    if not binary:
-        pytest.skip("llama-server binary not found — install llama-cpp-turboquant")
-        return
-    
-    model = find_model()
-    if not model:
-        pytest.skip("No GGUF model found — set TURBOQUANT_MODEL_DIR or place model in ~/models")
-        return
-    
-    port = int(os.environ.get("TURBOQUANT_TEST_PORT", "18081"))
-    kv_type = os.environ.get("TURBOQUANT_KV_TYPE", "turbo4")
-    ctx_size = int(os.environ.get("TURBOQUANT_CTX_SIZE", "8192"))
-    timeout = float(os.environ.get("TURBOQUANT_STARTUP_TIMEOUT", "60"))
-    
-    server = TurboQuantServer(
-        model_path=model,
-        port=port,
-        kv_type=kv_type,
-        context_size=ctx_size,
-        server_binary=binary,
-        timeout=timeout,
-    )
-    
-    try:
-        url = server.start()
-        yield url
-    except Exception as e:
-        pytest.skip(f"Could not start TurboQuant server: {e}")
-    finally:
-        server.stop()
-
-
-@pytest.fixture(scope="session")
-def turboquant_model_name(turboquant_server_url):
-    """Get the model name from the running server."""
-    import json
-    import urllib.request
-    
-    try:
-        req = urllib.request.Request(f"{turboquant_server_url}/v1/models")
-        resp = urllib.request.urlopen(req, timeout=10)
-        data = json.loads(resp.read())
-        models = data.get("data", [])
-        if models:
-            return models[0].get("id", "unknown")
-    except Exception:
-        pass
-    return "gemma-4"

tests/server_manager.py

@@ -1,197 +0,0 @@
-#!/usr/bin/env python3
-"""
-TurboQuant Server Manager
-
-Manages llama-server lifecycle for integration tests:
-- Start server with TurboQuant flags
-- Wait for health check
-- Stop server on teardown
-
-Usage:
-    from tests.server_manager import TurboQuantServer
-    
-    with TurboQuantServer(model_path="/path/to/model.gguf") as server:
-        url = server.url  # e.g. http://localhost:8081
-        # Run tests against server
-"""
-
-import json
-import os
-import signal
-import subprocess
-import sys
-import time
-import urllib.request
-import urllib.error
-from pathlib import Path
-from typing import Optional
-
-
-class TurboQuantServer:
-    """Context manager for llama-server with TurboQuant."""
-    
-    def __init__(
-        self,
-        model_path: str,
-        port: int = 8081,
-        kv_type: str = "turbo4",
-        context_size: int = 32768,
-        server_binary: Optional[str] = None,
-        timeout: float = 60.0,
-        host: str = "127.0.0.1",
-    ):
-        self.model_path = model_path
-        self.port = port
-        self.kv_type = kv_type
-        self.context_size = context_size
-        self.timeout = timeout
-        self.host = host
-        
-        # Find server binary
-        if server_binary:
-            self.server_binary = server_binary
-        else:
-            # Try common locations
-            candidates = [
-                Path.home() / "llama-cpp-turboquant" / "build" / "bin" / "llama-server",
-                Path("/opt/llama-cpp-turboquant/build/bin/llama-server"),
-                Path("llama-server"),  # PATH
-            ]
-            self.server_binary = None
-            for c in candidates:
-                if c.exists() or c.name == "llama-server":
-                    try:
-                        subprocess.run([str(c), "--help"], capture_output=True, timeout=5)
-                        self.server_binary = str(c)
-                        break
-                    except (FileNotFoundError, subprocess.TimeoutExpired):
-                        continue
-        
-        self.process: Optional[subprocess.Popen] = None
-    
-    @property
-    def url(self) -> str:
-        return f"http://{self.host}:{self.port}"
-    
-    def _build_command(self) -> list:
-        cmd = [
-            self.server_binary,
-            "-m", self.model_path,
-            "--port", str(self.port),
-            "--host", self.host,
-            "-ctk", self.kv_type,
-            "-ctv", self.kv_type,
-            "-c", str(self.context_size),
-        ]
-        return cmd
-    
-    def _check_health(self) -> bool:
-        try:
-            req = urllib.request.Request(f"{self.url}/v1/models")
-            resp = urllib.request.urlopen(req, timeout=5)
-            data = json.loads(resp.read())
-            return "data" in data and len(data.get("data", [])) > 0
-        except Exception:
-            return False
-    
-    def start(self) -> str:
-        """Start the server and wait for it to be healthy. Returns the server URL."""
-        if not self.server_binary:
-            raise RuntimeError(
-                "llama-server binary not found. Set server_binary or install to standard location."
-            )
-        
-        if not Path(self.model_path).exists():
-            raise FileNotFoundError(f"Model not found: {self.model_path}")
-        
-        cmd = self._build_command()
-        
-        # Set TurboQuant env
-        env = os.environ.copy()
-        env["TURBO_LAYER_ADAPTIVE"] = "7"
-        
-        self.process = subprocess.Popen(
-            cmd,
-            stdout=subprocess.PIPE,
-            stderr=subprocess.PIPE,
-            env=env,
-        )
-        
-        # Wait for health
-        start = time.time()
-        while time.time() - start < self.timeout:
-            if self.process.poll() is not None:
-                stderr = self.process.stderr.read().decode() if self.process.stderr else ""
-                raise RuntimeError(f"Server exited early (code {self.process.returncode}): {stderr[:500]}")
-            
-            if self._check_health():
-                return self.url
-            
-            time.sleep(1.0)
-        
-        self.stop()
-        raise TimeoutError(f"Server did not become healthy within {self.timeout}s")
-    
-    def stop(self):
-        """Stop the server."""
-        if self.process:
-            try:
-                self.process.send_signal(signal.SIGTERM)
-                self.process.wait(timeout=10)
-            except subprocess.TimeoutExpired:
-                self.process.kill()
-                self.process.wait(timeout=5)
-            except Exception:
-                pass
-            self.process = None
-    
-    def __enter__(self) -> "TurboQuantServer":
-        self.start()
-        return self
-    
-    def __exit__(self, *args):
-        self.stop()
-
-
-def find_server_binary() -> Optional[str]:
-    """Find llama-server binary in common locations."""
-    candidates = [
-        Path.home() / "llama-cpp-turboquant" / "build" / "bin" / "llama-server",
-        Path("/opt/llama-cpp-turboquant/build/bin/llama-server"),
-    ]
-    for c in candidates:
-        if c.exists():
-            return str(c)
-    
-    # Try PATH
-    try:
-        result = subprocess.run(["which", "llama-server"], capture_output=True, text=True)
-        if result.returncode == 0:
-            return result.stdout.strip()
-    except Exception:
-        pass
-    
-    return None
-
-
-def find_model(model_dir: Optional[str] = None) -> Optional[str]:
-    """Find a GGUF model file."""
-    search_dirs = [
-        model_dir,
-        os.environ.get("TURBOQUANT_MODEL_DIR"),
-        str(Path.home() / "models"),
-        "/opt/models",
-        "/tmp/models",
-    ]
-    
-    for d in search_dirs:
-        if not d:
-            continue
-        p = Path(d)
-        if p.is_file() and p.suffix == ".gguf":
-            return str(p)
-        if p.is_dir():
-            for f in sorted(p.rglob("*.gguf")):
-                return str(f)
-    
-    return None

tests/test_dflash_apple_silicon.py

@@ -0,0 +1,58 @@
+#!/usr/bin/env python3
+"""Tests for Apple Silicon DFlash benchmark planning helpers (issue #152)."""
+
+import os
+import sys
+from unittest.mock import patch
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(__file__)))
+
+from benchmarks.dflash_apple_silicon import (  # noqa: E402
+    build_mlx_benchmark_command,
+    detect_total_memory_gb,
+    render_report_template,
+    select_pair,
+)
+
+
+class TestPairSelection:
+    def test_prefers_qwen35_9b_on_36gb_mac(self):
+        pair = select_pair(total_memory_gb=36)
+        assert pair.slug == "qwen35-9b"
+        assert pair.base_model == "Qwen/Qwen3.5-9B"
+        assert pair.draft_model == "z-lab/Qwen3.5-9B-DFlash"
+
+    def test_falls_back_to_4b_when_memory_is_tight(self):
+        pair = select_pair(total_memory_gb=20)
+        assert pair.slug == "qwen35-4b"
+        assert pair.base_model == "Qwen/Qwen3.5-4B"
+
+
+class TestCommandGeneration:
+    def test_builds_upstream_mlx_benchmark_command(self):
+        pair = select_pair(total_memory_gb=36)
+        command = build_mlx_benchmark_command(pair, dataset="gsm8k", max_samples=64)
+        assert "python -m dflash.benchmark --backend mlx" in command
+        assert "--model Qwen/Qwen3.5-9B" in command
+        assert "--draft-model z-lab/Qwen3.5-9B-DFlash" in command
+        assert "--dataset gsm8k" in command
+        assert "--max-samples 64" in command
+        assert "--draft-sliding-window-size 4096" in command
+
+
+class TestReportTemplate:
+    def test_report_template_mentions_baseline_and_verdict(self):
+        pair = select_pair(total_memory_gb=36)
+        report = render_report_template(machine_label="M3 Max 36GB", pair=pair)
+        assert "DFlash Apple Silicon Benchmark Report" in report
+        assert "M3 Max 36GB" in report
+        assert "Qwen/Qwen3.5-9B" in report
+        assert "plain MLX or llama.cpp speculative decoding" in report
+        assert "Worth operationalizing locally?" in report
+
+
+class TestMemoryDetection:
+    @patch("benchmarks.dflash_apple_silicon.platform.system", return_value="Darwin")
+    @patch("benchmarks.dflash_apple_silicon.subprocess.check_output", return_value=b"38654705664\n")
+    def test_detect_total_memory_gb_on_macos(self, _mock_sysctl, _mock_system):
+        assert detect_total_memory_gb() == 36.0

tests/test_quant_selector.py

@@ -19,10 +19,11 @@ from evolution.quant_selector import (
 
 
 class TestQuantLevels:
-    def test_levels_ordered_by_quality(self):
-        """Levels should be ordered from best quality to most aggressive."""
-        for i in range(len(QUANT_LEVELS) - 1):
-            assert QUANT_LEVELS[i].bits_per_channel > QUANT_LEVELS[i + 1].bits_per_channel
+    def test_levels_keep_turboquant_quality_order_with_q4_fallback_last(self):
+        """TurboQuant levels should lead, with q4_0 reserved as the non-Turbo fallback."""
+        names = [level.name for level in QUANT_LEVELS]
+        assert names[:3] == ["turbo4", "turbo3", "turbo2"]
+        assert names[-1] == "q4_0"
 
     def test_all_levels_have_required_fields(self):
         for level in QUANT_LEVELS:
@@ -148,6 +149,19 @@ class TestSelection:
             sel = select_quant_level(model_size_gb=16.0, context_length=65536)
             assert len(sel.warnings) > 0
 
+    def test_falls_back_to_turbo2_when_nothing_fits(self):
+        with patch("evolution.quant_selector.detect_hardware") as mock_hw:
+            mock_hw.return_value = HardwareInfo(
+                total_memory_gb=8,
+                available_memory_gb=6,
+                gpu_memory_gb=8,
+                gpu_name="Tiny GPU",
+                cpu_cores=4,
+                detection_method="mock",
+            )
+            sel = select_quant_level(model_size_gb=16.0, context_length=131072)
+            assert sel.level.name == "turbo2"
+
     def test_reasoning_contains_key_info(self):
         with patch("evolution.quant_selector.detect_hardware") as mock_hw:
             mock_hw.return_value = HardwareInfo(