dongarandClaude Opus 5.5 82f171c2f5 Benchmark seven new RTX 4090 models, and local-fast on the 4090 ...

Five runs per task for qwen3.8-27b, qwen3.6-35b-a3b, gemma-4-31b,
gemma-4-26b-a4b, gemma-4-12b, mimo-v2.6-9b and granite-4.2-8b, all
served by llama.cpp b11206 through llama-swap. Every one passed 20 of
20. local-fast (vLLM 0.30.0) passed 3 of 20.

Runs were made under a 350 W power cap, recorded in each note, after
the uncapped card throttled for heat. granite-4.2-8b also has one
uncapped set, kept apart by its note.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

2026-09-27 18:43:55 +00:00

..

.gitkeep

Add an executor benchmark that keeps its results

2026-09-25 00:35:24 +00:00

2026-09-25-local-coder.jsonl

Add the local baseline: qwen3-8b-awq and qwen3-14b, 5 runs per task

2026-09-25 01:25:13 +00:00

2026-09-25-local-fast.jsonl

Add the local baseline: qwen3-8b-awq and qwen3-14b, 5 runs per task

2026-09-25 01:25:13 +00:00

2026-09-27-gemma-4-12b.jsonl

Benchmark seven new RTX 4090 models, and local-fast on the 4090

2026-09-27 18:43:55 +00:00

2026-09-27-gemma-4-26b-a4b.jsonl

Benchmark seven new RTX 4090 models, and local-fast on the 4090

2026-09-27 18:43:55 +00:00

2026-09-27-gemma-4-31b.jsonl

Benchmark seven new RTX 4090 models, and local-fast on the 4090

2026-09-27 18:43:55 +00:00

2026-09-27-granite-4.2-8b.jsonl

Benchmark seven new RTX 4090 models, and local-fast on the 4090

2026-09-27 18:43:55 +00:00

2026-09-27-local-fast.jsonl

Benchmark seven new RTX 4090 models, and local-fast on the 4090

2026-09-27 18:43:55 +00:00

2026-09-27-mimo-v2.6-9b.jsonl

Benchmark seven new RTX 4090 models, and local-fast on the 4090

2026-09-27 18:43:55 +00:00

2026-09-27-qwen3.6-35b-a3b.jsonl

Benchmark seven new RTX 4090 models, and local-fast on the 4090

2026-09-27 18:43:55 +00:00

2026-09-27-qwen3.8-27b.jsonl

Benchmark seven new RTX 4090 models, and local-fast on the 4090

2026-09-27 18:43:55 +00:00