Qwen3.6 35B-A3B
Qwen3.6 35B-A3B
Architecture & parameters
| Parameters (total) | 36.0B |
|---|---|
| Parameters (active) | 3.0B |
| Architecture | qwen3_5_moe |
| Layers | 40 |
| KV heads | 2 |
| Native context | 262144 |
Artifacts
| File | Publisher | Format | Quant | Size | Link | Evidence |
|---|---|---|---|---|---|---|
Qwen3.6-35B-A3B-UD-Q5_K_M.gguf | Unsloth | gguf | UD-Q5_K_M | 24.64 GiB | source | SOURCE |
Qwen3.6-35B-A3B-UD-IQ4_XS.gguf | Unsloth | gguf | UD-IQ4_XS | 16.51 GiB | source | SOURCE |
VRAM (weights-only)
Not a full fit result. This classification considers artifact weights only. It does not include KV cache, runtime buffers, backend allocations, multimodal projectors, concurrency, or safety reserve.
| Component | Value | Evidence |
|---|---|---|
| Artifact weights | 24.64 GiB | SOURCE |
| KV cache | Not modeled | NOT KNOWN YET |
| Runtime buffers | Not modeled | NOT KNOWN YET |
| Safety reserve | Not modeled | NOT KNOWN YET |
| Weights-only memory class | 32gb+ | SOURCE POLICY |
Runtime support
Sources
- Hugging Face: https://huggingface.co/Qwen/Qwen3.6-35B-A3B
- Official: https://huggingface.co/Qwen/Qwen3.6-35B-A3B