Qwen 3.7 35B-A3B — VRAM, Speed & Local Setup

Written by Jakub Rusinowski · Last updated June 26, 2026

Model library → Qwen 3.7 → Qwen 3.7 35B-A3B

PREVIEW — unverified. ~35B-total MoE with ~3B active, native text/image/video, Apache 2.0, ~256K context. At Q4 (~21 GB) it fits a 24 GB card. Estimates carried from Qwen 3.6 35B-A3B — confirm on the Hugging Face model card.

Qwen 3.7 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 (multimodal)
ProviderAlibaba Cloud
LicenceApache 2.0
Specified atQ4_K_M
System RAM32 GB
Record updated2026-06-26

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 3.7 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 3.7 35B-A3B is the AMD Radeon RX 7900 XTX (24 GB).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
AMD Radeon RX 7900 XTX 24GB
24 GB VRAM · 355 W board power
2026 prices are volatile — check the current listing.
Check price on Amazon

How to Run Qwen 3.7 35B-A3B

Install Ollama, then run:

ollama run qwen3-7

Weights on Hugging Face: Qwen/Qwen3.7-35B-A3B.

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

Can I Run Qwen 3.7 35B-A3B on My GPU?

Qwen 3.7 35B-A3B — Frequently Asked Questions

How much VRAM does Qwen 3.7 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 3.7 35B-A3B run on an RTX 4090 (24 GB)?
Yes. Qwen 3.7 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 3.7 35B-A3B locally?
Install Ollama and run `ollama run qwen3-7`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

← All Qwen 3.7 models | VRAM calculator | Build a PC for this model | Check your own hardware