Qwen3.6
Qwen3.6-35B-A3B
Alibaba (Qwen team) · open-permissive apache-2.0
| Parameters (B) | 35.952 |
|---|---|
| Architecture | moe |
| Layers / KV heads / head dim | 40 / 2 / 256 |
| Context window | 262144 |
| Modalities | in: text, image; out: text |
| GGUF | available |
| Commercial use | yes |
Minimum hardware (estimate)
At Q4_K_M and 8k context, total working set ≈ 23.0 GiB. On a machine with 64 GiB system RAM and no discrete GPU: CPU-only, slow. Limiting factor: No GPU VRAM; fits in system RAM but inference will be CPU-bound.
Scores
| Benchmark | Value | Uncertainty | Run by | Source |
|---|---|---|---|---|
| GPQA Diamond | 84.9% | ±0.0255 | third-party | epoch-ai |
| OTIS Mock AIME 2024-2025 | 86.7% | ±0.0512 | third-party | epoch-ai |
| Terminal-Bench | 24.6% | ±0.0320 | third-party | epoch-ai |
Provenance
- identity, license, architecture, parameter count: https://huggingface.co/Qwen/Qwen3.6-35B-A3B (retrieved 2026-08-10)
HF: Qwen/Qwen3.6-35B-A3B · snapshot 2026-08-10