Qwen 3.6 35B-A3B — VRAM, Speed & Local Setup

作者： Jakub Rusinowski · 最后更新： 2026年4月16日

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.

Specifications

Parameters35 Billion (3B active)
Context window262,144
ArchitectureHybrid Gated DeltaNet + MoE (256 experts)
ProviderAlibaba Cloud
LicenceApache 2.0
Specified atQ4_K_M
System RAM32 GB
Record updated2026-04-16

Licence

Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). 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.

QuantWeightsVRAM neededEst. speedFit on 24 GB
Q2_K11.5 GB12.3 GB~209 tok/s (est.)Fits comfortably
Q3_K_M14.9 GB15.7 GB~193 tok/s (est.)Fits comfortably
Q4_K_M21.1 GB21.9 GB~170 tok/s (est.)Tight fit
Q5_K_M24.8 GB25.6 GB~24 tok/s (est.)Offloads to system RAM (slow)
Q6_K28.7 GB29.5 GB~22 tok/s (est.)Offloads to system RAM (slow)
Q8_037.2 GB38.0 GB~19 tok/s (est.)Offloads to system RAM (slow)
F1670.0 GB70.8 GB—Won't fit

Want the memory numbers alone, at every quantization level and your own context length? Use the Qwen 3.6 35B-A3B VRAM calculator.

Buy This HardwareAMD Radeon RX 7900 XTX 24GB — 24 GB VRAM · 355 W board powerDeploy in the Cloud NowRTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

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.

Recommended GPU

The cheapest catalogued GPU that runs Qwen 3.6 35B-A3B is the AMD Radeon RX 7900 XTX (24 GB).

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买，LLM Configurator 可能会获得佣金，而你无需支付任何额外费用。作为亚马逊联盟成员（Amazon Associate），LLM Configurator 会从符合条件的购买中获得收益。
AMD Radeon RX 7900 XTX 24GB
24 GB VRAM · 355 W board power
2026年价格波动较大——请以当前商品页价格为准。
在亚马逊查看价格

How to Run Qwen 3.6 35B-A3B

Install Ollama, then run:

ollama run qwen3.6:35b-a3b

Weights on Hugging Face: Qwen/Qwen3.6-35B-A3B.

Best for: reasoning, coding, multimodal, consumer gpu.

Can I Run Qwen 3.6 35B-A3B on My GPU?

Other Qwen 3.6 Sizes

Qwen 3.6 35B-A3B — Frequently Asked Questions

How much VRAM does Qwen 3.6 35B-A3B need?
About 22 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Qwen 3.6 35B-A3B run on an RTX 4090 (24 GB)?
Yes. Qwen 3.6 35B-A3B needs about 22 GB at Q4_K_M, inside a 24 GB card, at an estimated 170 tokens/sec.
How do I run Qwen 3.6 35B-A3B locally?
Install Ollama and run `ollama run qwen3.6:35b-a3b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Qwen 3.6 come in?
Qwen 3.6 27B (18 GB), Qwen 3.6 35B-A3B (22 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All Qwen 3.6 models | VRAM calculator | Build a PC for this model | Check your own hardware