Autor: Jakub Rusinowski · Ostatnia aktualizacja: 16 kwietnia 2026
Model library → Qwen 3.6 → Qwen 3.6 35B-A3B
MoE successor to Qwen 3.5 35B-A3B, now with native image AND video input (3.5 was image-only). Q4_K_M is ~21 GB — fits a 24GB GPU, though a 32GB card (RTX 5090) leaves more headroom for KV cache at long context. Community reports running it on 6GB VRAM via heavy CPU offload at ~30 tok/s.
Qwen 3.6 35B-A3B needs about 22 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
| Parameters | 35 Billion (3B active) |
| Context window | 262,144 |
| Architecture | Hybrid Gated DeltaNet + MoE (256 experts) |
| Provider | Alibaba Cloud |
| Licence | Apache 2.0 |
| Specified at | Q4_K_M |
| System RAM | 32 GB |
| Record updated | 2026-04-16 |
Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.
Modelled on a reference NVIDIA RTX 4090 (24 GB). Weights plus framework overhead only — this model publishes no architecture we can read, so no KV cache is included. A real session needs more; the figure is a floor, not a target. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.
| Quant | Bits/weight | Weights | VRAM needed | Est. speed | Fit on 24 GB |
|---|---|---|---|---|---|
| Q2_K | 2.63 | 11.5 GB | 12.3 GB | ~209 tok/s (est.) | Fits comfortably |
| Q3_K_M | 3.41 | 14.9 GB | 15.7 GB | ~193 tok/s (est.) | Fits comfortably |
| Q4_K_M | 4.83 | 21.1 GB | 21.9 GB | ~170 tok/s (est.) | Tight fit |
| Q5_K_M | 5.67 | 24.8 GB | 25.6 GB | ~24 tok/s (est.) | Offloads to system RAM (slow) |
| Q6_K | 6.56 | 28.7 GB | 29.5 GB | ~22 tok/s (est.) | Offloads to system RAM (slow) |
| Q8_0 | 8.50 | 37.2 GB | 38 GB | ~19 tok/s (est.) | Offloads to system RAM (slow) |
| F16 | 16.00 | 70 GB | 70.8 GB | — | Won't fit |
Want to set your own context length and KV-cache quantization? Use the interactive VRAM calculator.
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
The cheapest catalogued GPU that runs Qwen 3.6 35B-A3B is the AMD Radeon RX 7900 XTX (24 GB).
Install Ollama, then run:
ollama run qwen3.6:35b-a3bWeights on Hugging Face: Qwen/Qwen3.6-35B-A3B.
Best for: reasoning, coding, multimodal, consumer gpu.
← All Qwen 3.6 models | VRAM calculator | Build a PC for this model | Check your own hardware