Runs on ≤32 GB · Hugging Face ↗
Not independently scored by Artificial Analysis
Version 1.5 of the self-scaffolding agentic coder whose 9B and 35B we already measure (MIT). 36B MoE with 3B active.
BigCodeBench-Hard pass@1 27% (40/148), via official protocol · llama.cpp Q4_K_M · one request at a time · a shared cluster GPU · mean of 3 runs, range 0.0 pp. The brutal counterpart to HumanEval — where HumanEval saturates near the top, BCB-Hard spreads the field, so this is the number that actually separates coding ability.
Our own runs on this model. Each number carries how many problems it is over and how many times we ran it — these are not comparable with each other, and none of them is on the same scale as the third-party indices on the leaderboard.
| test | score | over | conditions |
|---|---|---|---|
| BigCodeBench-Hard | 27.0% | n=148 · 3 run(s) | official protocol · llama.cpp Q4_K_M · one request at a time · a shared cluster GPU · mean of 3 runs, range 0. |
Real GGUF file sizes = weight VRAM. Add the KV cache for your context (≈1 GB at 32K, fp16). Read from the GGUF header and checked against what llama.cpp actually allocates.
| Quantization | Size |
|---|---|
| Q4_K_M | 21.7 GB |
| Q5_K_M | 25.3 GB |
| Q6_K | 29.2 GB |
| Q8_0 | 37.8 GB |
| BF16 | 71.1 GB |
27.0% over three runs. Built for AGENTIC coding with tools, so a single-shot benchmark like ours reads as a floor, not a ceiling.