Alexander Payne d3ee6edd15 bench: add Bonsai 1-bit vs Q4_0 comparison benchmark — issue #100 ...

- Add benchmarks/run_bonsai_compare.py (script + quality scores)
- Add benchmarks/bonsai-1bit-comparison-2025-10-06.md (published M4 Pro refs)
- Add bonsai_results_seed.json with published numbers
- README link to new benchmark page

Closes #100

2026-04-30 02:48:37 -04:00

..

bonsai_results_2026-04-30.json

bench: add Bonsai 1-bit vs Q4_0 comparison benchmark — issue #100

2026-04-30 02:48:37 -04:00

bonsai_results_seed.json

bench: add Bonsai 1-bit vs Q4_0 comparison benchmark — issue #100

2026-04-30 02:48:37 -04:00

bonsai-1bit-comparison-2025-10-06.md

bench: add Bonsai 1-bit vs Q4_0 comparison benchmark — issue #100

2026-04-30 02:48:37 -04:00

perplexity_results.json

feat: wikitext-2 corpus + perplexity benchmark script (closes #21)

2026-04-12 00:39:14 -04:00

prompts.json

feat: add standardized benchmarking prompts

2026-03-30 21:14:48 +00:00

run_benchmarks.py

feat: multi-backend benchmark suite with TTFT + memory tracking (#37)

2026-04-13 14:05:17 +00:00

run_bonsai_compare.py

bench: add Bonsai 1-bit vs Q4_0 comparison benchmark — issue #100

2026-04-30 02:48:37 -04:00

run_long_session.py

burn: add long-session quality test (Issue #12) (#39)

2026-04-13 19:59:22 +00:00

run_perplexity.py

feat: wikitext-2 corpus + perplexity benchmark script (closes #21)

2026-04-12 00:39:14 -04:00

test_prompts.json

Add benchmark test prompts for quality comparison (Issue #22)

2026-03-31 17:31:05 +00:00