Python · MIT
SergiioB/intel-arc-pro-b70-inference-cookbook
Pinned Intel Arc Pro B60/B70 inference recipes, engine patches and measurement records: Qwen3.8-27B EXL3 on one card (262,144 context, 63 tok/s; MTP3 measured lossy on 27% of a fixed 329-item set), Nemotron Bolt 74B, Flash-Next, dual-card routes, and a machine-checked catalog where each speculative row states whether the drafter changes the answer.
★ 192
Stars
13 forks · 2 open issues
+4.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
25.4
Momentum / 100
see the breakdown below
3mo ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 3.8 | +4.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.87× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 6.6 | 192 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 25.4 | sum of the above |
Detail
| Topics | battlemageintel-arcintel-arc-b70intel-gpullama-cppllm-inferencelocal-aimoemtpspeculative-decodingsyclvllm |
| Matched on | LLM & Inference (llm-inference) |
| Short window | +4 stars over 7 days = 0.6/day |
| Long window | +17 stars over 26 days = 0.7/day |
| Lifetime average | 2.11 stars/day over 91 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |