Qwen3 8B VRAM requirements

How much VRAM does Qwen3 8B need?

Qwen3 8B needs 6.81 GB at Q4_K_M, 10.7 GB at Q8_0 and 18.5 GB at FP16 with 8,192 tokens of context and one request. Each total below is the weights plus the FP16 KV cache and the runtime overhead (0.5 GB plus 10%), and each row opens the calculator with that setting. What the GGUF names mean.

Fine-tuning Qwen3 8B? Qwen3 8B VRAM for LoRA, QLoRA and full training.

Qwen3 8B GGUF files on Hugging Face

The 8 GGUF files llama.cpp picks for Qwen3 8B with -hf <repo>:<QUANT>, with the bytes the Hugging Face file list reported on 2026-09-29. Each total is that file plus the FP16 KV cache and 0.5 GB + 10%, one request. "vs estimate" compares the file with the bits-per-weight size the table above uses.

GB here is GiB (1024³ bytes), as everywhere on this site; Hugging Face shows the Q4_K_M file as 5.0 GB, in 10⁹ bytes.

Which Qwen3 8B GGUF fits a 16, 24, 32, 48 or 80 GB GPU or a Mac

From the file sizes above: the largest file that fits each machine with an 8K context and 0.5 GB left free, the longest context it then has room for, and the longest context for Q4_K_M (4.68 GB). One request, FP16 KV cache.

Run Qwen3 8B with llama.cpp or Ollama

llama-server -hf unsloth/Qwen3-8B-GGUF:Q4_K_M -c 40960

Qwen3-8B-Q4_K_M.gguf, 5.0 GB, from unsloth/Qwen3-8B-GGUF (checked 2026-09-29). On a 24 GB RTX 3090 / 4090, Q4_K_M with -c 40960 takes 11.8 GB and leaves 12.2 GB.

ollama run qwen3:8b

Ollama library tag qwen3:8b; its quant is Ollama's choice. Same context: /set parameter num_ctx 40960.

Qwen3 8B at 8K, 32K and 40K (full) tokens of context

All 36 layers use full attention. Each extra token of context adds 144 KB of FP16 cache per request. The last column is the smallest setup here, one card or a group, that holds it at Q4_K_M. How the KV cache works.

How fast Qwen3 8B writes

Tokens per second for one request with 8,192 tokens of context, estimated from memory bandwidth. A dash means it does not fit on one card. Try other settings in the speed calculator.

Longest context on one GPU

How many tokens of context Qwen3 8B fits on a single card with one request, an FP16 KV cache and 0.5 GB left free. "Full" means the model's whole context window fits.

Model details

Parameters

8.2B (8,190,735,360)

Layers

All 36 layers use full attention

Attention cache

8 KV heads × 128

Context length

40,960 tokens

Published weights

15.3 GB (BF16)

On Hugging Face

Qwen/Qwen3-8B

Reported benchmarks

None published in the model card for GPQA, MMLU-Pro or LiveCodeBench.

Qwen3 8B next to similar-sized models

The three models here closest to it in parameter count, at Q4_K_M with 8,192 tokens of context.