Runs on ≤32 GB · Hugging Face ↗
Not independently scored by Artificial Analysis — its base model Qwen3.6-35B-A3B is the closest proxy
Kwaipilot's agentic coder — a 35B-total Qwen3.5-MoE (the same architecture family as Ornith 35B), Apache-2.0, tagged code + agent. Trending on Hugging Face yet unscored by AA, so exactly the kind of capable open coder the index misses.
Real GGUF file sizes = weight VRAM.
| Quantization | Size |
|---|---|
| Q3_K_M | 16.2 GB |
| IQ4_XS | 18.8 GB |
| Q4_0 | 19.9 GB |
| Q4_K_S | 20.6 GB |
| Q4_K_M | 21.4 GB |
| Q4 | 21.8 GB |
| Q4_1 | 22.0 GB |
| Q5_K_M | 25.0 GB |
| Q2_K | 25.7 GB |
| Q8_0 | 36.9 GB |
| Q6_K | 60.4 GB |
| BF16 | 69.4 GB |
~20 GB at Q4 — spills past a 16 GB card, comfortable on 24 GB+ or the 32 GB tier. MoE, so only a few billion params compute per token; built for multi-turn agentic coding, so a single-shot BCB understates it. (Unmeasured — genuinely hard to benchmark. It's a vision-language model, so vLLM 0.26 won't load it (visual-tower weights missing) AND its text-only GGUF loads in Ollama but generates empty output. Needs a runtime that handles the full VL model.)