Qwen3 8B

Qwen — 8B params — Q4_K_M, local via Ollama. Dataset updated 2026-09-03.

PARAMETERS
8B
FORMAT
Q4_K_M
MIN MEMORY
12 GB
BEST FOR
Chat, Coding

Memory math

Weights (Q4_K_M)
6.5 GB
+ KV cache (16k)
~2.0 GB
Total at 16k
~8.5 GB
Comfortable from
16 GB

KV = fp16 estimate (q8_0 cache roughly halves it). "Comfortable" = weights + KV within the engine's tiered budget (~70-85% of memory).

Hardware snapshot

Cheapest GPU
~74 tok/s est. — ~$550 used
Fastest
~145 tok/s est.
Runs on a Mac?
~28 tok/s est.

Go deeper

Every Qwen3 8B quant by real GGUF file sizeBest hardware for Qwen3 8B: cheapest, best value, fastestVerdict: qwen3 8b q4 on rtx 3060Verdict: qwen3 8b q4 on rtx 4060Verdict: qwen3 8b q4 on rtx 4060 tiVerdict: qwen3 8b q4 on rtx 4070Also tracked: Qwen3 8B (Q8) (Q8_0, 8.1 GB, min 16 GB)

More Qwen models

Qwen3.7-PlusQwen2.5 0.5B InstructQwen3.5 0.8B InstructQwen2.5 1.5B InstructQwen3.5 2B InstructQwen2.5 3B InstructQwen3.5 4B InstructQwen2.5 7B InstructQwen2.5 Coder 7BQwen3.5 9B InstructQwen2.5 14B InstructQwen2.5 Coder 14BQwen3 14BQwen3.5 27B InstructQwen3.6 27BQwen3.8 27BQwen3 30BQwen3 30B (Q8)Qwen3.5 35B-A3B InstructQwen3.6 35B-A3BQwen3-Next 80B-A3BQwen3.5 122B-A10B InstructQwen3.8-Flash-NextQwen3 235B A22B

Frequently asked questions

How much memory does Qwen3 8B need?

6.5 GB for the Q4_K_M weights, plus ~2.0 GB of KV-cache at 16k context — about 8.5 GB total. Comfortable from 16 GB of VRAM or unified memory.

Does Qwen3 8B run on a Mac?

Yes — from the Mac Mini M6 16GB (~28 tok/s est.). Unified memory means the RAM budget is the only limit.

What is the cheapest GPU for Qwen3 8B?

The AMD Radeon RX 7900 XT is the cheapest tracked card that runs Qwen3 8B comfortably — ~74 tok/s est. at ~$550 used.

Cite this page

ModelFit: Qwen3 8B — specs, memory math and hardware verdicts.
https://modelfit.io/models/qwen3-8b/ (dataset updated 2026-09-03, CC BY 4.0).