Alibaba Cloud8B~6 GB VRAM at Q4_K_M

Qwen 3 8B — VRAM, speed & local setup

Written by Jakub Rusinowski · Last updated

Qwen 3's accessible dense model with hybrid thinking. Toggle /think for deep reasoning or /no_think for fast responses. Outperforms DeepSeek R1 Distill 8B on many benchmarks at the same VRAM footprint.

Qwen 3 8B needs about 6 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.

Logic90
Creative80
Coding88

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.

QuantVRAMSpeed (est.)Fit
Q2_K
2.63 bpw
4.7 GB~151 tok/sFits
Q3_K_M
3.41 bpw
5.5 GB~130 tok/sFits
Q4_K_M
4.83 bpw
7 GB~141 tok/s · measuredFits
Q5_K_M
5.67 bpw
7.8 GB~93 tok/sFits
Q6_K
6.56 bpw
8.7 GB~84 tok/sFits
Q8_0
8.50 bpw
10.7 GB~69 tok/sFits
F16
16.00 bpw
18.4 GB~40 tok/sFits

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Qwen 3 8B VRAM calculator →

Get Qwen 3 8B running

The cheapest catalogued GPU that runs Qwen 3 8B is the Intel Arc B570 (10 GB).

Buy this hardware Intel Arc B570 10GB — 10 GB VRAM · 150 W board powerDeploy in the cloud now RTX 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.

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.
Intel Arc B570 10GB
10 GB VRAM · 150 W board power
2026 prices are volatile — check the current listing.

How to run Qwen 3 8B

Install Ollama, then run:

ollama run qwen3:8b
Weights on Hugging Face: Qwen/Qwen3-8B ↗

Specifications

Curated — A hand-written entry from before this catalogue recorded its sources. The figures are long-standing but their provenance is not on file.

Parameters
8 Billion
Context window
128,000
Architecture
Dense
Provider
Alibaba Cloud
Licence
Apache 2.0
Practical deployment
Laptop
Specified at
Q4_K_M
System RAM
16 GB
Record updated
2025-04-28
LicenceApache-2.0Commercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best forreasoningcodingchatbalanced

Can I run Qwen 3 8B on my GPU?

Other Qwen 3 sizes

Qwen 3 8B — frequently asked questions

How much VRAM does Qwen 3 8B need?

About 6 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 8B run on an RTX 4090 (24 GB)?

Yes. Qwen 3 8B needs about 6 GB at Q4_K_M, inside a 24 GB card, at an estimated 141 tokens/sec.

How do I run Qwen 3 8B locally?

Install Ollama and run `ollama run qwen3:8b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does Qwen 3 come in?

Qwen 3 8B (6 GB), Qwen 3 14B (10 GB), Qwen 3 32B (21 GB), Qwen 3 30B-A3B (MoE) (19 GB), Qwen 3 235B-A22B (MoE) (143 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.