Activity - turboquant - Hermes Gitea

Timmy_Foundation/turboquant

0 Active Pull Requests

8 Active Issues

0
Merged Pull Requests 0
Proposed Pull Requests 8
Closed Issues 0
New Issues

8 Issues closed from 1 user

Closed #24 [P2-4] Run full quality comparison: turbo4 vs f16 on 10 test prompts 2026-04-05 21:58:15 +00:00

Closed #1 TurboQuant — KV Cache Compression for Local Inference on M4 Max 2026-04-05 14:05:51 +00:00

Closed #25 [P2-5] Download qwen3.5:27b and benchmark turbo4 at 64K/128K context 2026-04-05 14:05:50 +00:00

Closed #23 [P2-3] Fix Ollama install and build custom Ollama with TurboQuant fork 2026-04-05 14:05:50 +00:00

Closed #26 [P2-6] Production cutover: swap Timmy's llama-server to TurboQuant 2026-04-05 14:05:49 +00:00

Closed #27 [TQ-2] Build TheTom/llama-cpp-turboquant for M3 Max Metal 2026-04-05 14:05:49 +00:00

Closed #30 [EPIC] TurboQuant + Gemma 4 Local Mac Deployment 2026-04-05 14:05:48 +00:00

Closed #31 [TQ-1] Download Gemma 4 via Ollama on Mac 2026-04-05 14:05:48 +00:00

10 Unresolved Conversations

Open #29 [TQ-5] Benchmark: latency, memory, quality comparison 2026-04-06 07:21:31 +00:00

Open #28 [TQ-4] Create Hermes profile for local Gemma 4 + TurboQuant 2026-04-06 04:45:27 +00:00

Open #32 [TQ-3] Perplexity quality gate: turbo4 vs f16 2026-04-06 04:00:27 +00:00

Open #21 [P2-1] Download wikitext-2-raw and run perplexity quality gate 2026-04-05 22:00:49 +00:00

Open #22 [P2-2] Write 10 test prompts for quality comparison 2026-04-05 22:00:49 +00:00

Open #17 TurboQuant Initiative Review & Contributor Feedback 2026-04-05 22:00:48 +00:00

Open #15 [P4] Upstream llama.cpp / Ollama TurboQuant watch 2026-04-05 22:00:48 +00:00

Open #16 [P1-PREP] Write 10 predefined test prompts 2026-04-05 22:00:48 +00:00

Open #11 [P2] Full test matrix — 10 prompts + quality + performance 2026-04-05 22:00:47 +00:00

Open #12 [P2] Long-session quality test — 50-turn conversation 2026-04-05 22:00:47 +00:00