ochenstarik/hermes-hub
1
0
Fork 0
Code Issues Pull requests Projects Releases 13 Packages Wiki Activity Actions
hermes-hub/benchmarks
History
ochenstarik-ui 8c6bc7a7ed feat(benchmarks): benchmark three new local coder candidates on Tesla V100 (A45) 
- Measure Qwen3-Coder-30B-A3B, Qwen2.5-Coder-32B, and Tiel-Coder-35B-A3B at 64k and 32k context
- Verify long-context degradation profile and MoE attention scaling
- Add benchmark suite and results to BENCHMARK_MOE_CANDIDATES.md and benchmark_moe_results.json
2026-08-31 13:18:58 +07:00
..
__init__.py feat(benchmarks): benchmark three new local coder candidates on Tesla V100 (A45) 2026-08-31 13:18:58 +07:00
BENCHMARK_MOE_CANDIDATES.md feat(benchmarks): benchmark three new local coder candidates on Tesla V100 (A45) 2026-08-31 13:18:58 +07:00
benchmark_moe_results.json feat(benchmarks): benchmark three new local coder candidates on Tesla V100 (A45) 2026-08-31 13:18:58 +07:00
benchmark_suite.py feat(benchmarks): benchmark three new local coder candidates on Tesla V100 (A45) 2026-08-31 13:18:58 +07:00
fast_downloader.py feat(benchmarks): benchmark three new local coder candidates on Tesla V100 (A45) 2026-08-31 13:18:58 +07:00
measure_exact_moe_vram.py feat(benchmarks): benchmark three new local coder candidates on Tesla V100 (A45) 2026-08-31 13:18:58 +07:00
run_moe_benchmark.py feat(benchmarks): benchmark three new local coder candidates on Tesla V100 (A45) 2026-08-31 13:18:58 +07:00