Buckets:
7.62 GB
110 files
Updated 9 days ago
Ctrl+K
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| goldens | 1 items | ||
| packed | 92 items | ||
| .gitattributes | 1.57 kB xet | aacf151a | |
| BOARD.md | 2.49 kB xet | 82f16803 | |
| LICENSE | 11.3 kB xet | e630c17b | |
| MANIFEST.json | 337 Bytes xet | dfbc940c | |
| README.md | 2.26 kB xet | 04058d73 | |
| RELEASE_NOTES.md | 832 Bytes xet | 7c3238ab | |
| chat_template.jinja | 7.76 kB xet | ad35e2aa | |
| config.json | 3.14 kB xet | 7ff92bb6 | |
| decode.py | 41.6 kB xet | e94d774e | |
| extras.safetensors | 52.3 MB xet | 9177304d | |
| generation_config.json | 202 Bytes xet | 5aa9da2a | |
| merges.txt | 3.35 MB xet | ee5016b0 | |
| preprocessor_config.json | 390 Bytes xet | 2fd90549 | |
| tokenizer.json | 12.8 MB xet | 655d3f68 | |
| tokenizer_config.json | 16.7 kB xet | 3d4f1209 | |
| video_preprocessor_config.json | 385 Bytes xet | da843e00 | |
| vocab.json | 6.72 MB xet | 88980fb1 |
Benchmarks
Mach-1 Small is compared against its own BF16 teacher, as is every other model here. Retention = 100 × student score ÷ that student's own BF16 teacher score — a compression-fidelity measure, not an absolute capability score across model families.
| Mean retention, 12 benchmarks | |
|---|---|
| Mach-1 Small | 95.0% |
| Ternary Bonsai 27B (PrismML) | 94.4%† |
| Gemma 4 Q2_K_XL (Unsloth) | 85.6% |
Per-benchmark
| Benchmark | Mach-1 Small | Ternary Bonsai 27B | Gemma 4 Q2_K_XL |
|---|---|---|---|
| AIME26 | 99.5% | 93.8%† | 67.7% |
| MATH-500 | 99.4% | 98.2% | 95.6% |
| AIME25 | 99.1% | 97.4%† | 67.2% |
| GSM8K | 98.4% | 100.2% | 97.3% |
| MBPP+ | 98.3% | 98.4% | 92.2% |
| HumanEval+ | 97.4% | 98.7% | 94.1% |
| MMLU-Redux | 96.2% | 94.0% | 96.9% |
| IFEval | 94.0% | 89.8% | 95.5% |
| MuSR | 92.7% | 91.6% | 91.1% |
| BFCL-v3 | 92.0% | 98.9% | 95.7% |
| τ²-bench | 90.0% | 93.5% | 73.1% |
| IFBench | 83.2% | 77.7% | 61.3% |
| Mean | 95.0% | 94.4%† | 85.6% |
Mach-1 Small's own scores and teacher scores:
| Benchmark | Score | Teacher (Qwen3.6-35B-A3B BF16) | Retention |
|---|---|---|---|
| AIME26 | 89.58 | 90.00 | 99.5% |
| MATH-500 | 98.00 | 98.60 | 99.4% |
| AIME25 | 87.50 | 88.33 | 99.1% |
| GSM8K | 94.69 | 96.21 | 98.4% |
| MBPP+ | 94.44 | 96.03 | 98.3% |
| HumanEval+ | 92.68 | 95.12 | 97.4% |
| MMLU-Redux | 89.18 | 92.68 | 96.2% |
| IFEval | 83.75 | 89.05 | 94.0% |
| MuSR | 61.77 | 66.66 | 92.7% |
| BFCL-v3 | 68.97 | 74.98 | 92.0% |
| τ²-bench | 71.58 | 79.51 | 90.0% |
| IFBench | 54.08 | 64.97 | 83.2% |
Speed
- Total size
- 7.62 GB
- Files
- 110
- Last updated
- Aug 4
- Pre-warmed CDN
- US EU US EU