Qwen3-8B-GGUF
See our collection for all versions of Qwen3 including GGUF, 4-bit & 16-bit formats. Learn to run Qwen3 correctly - Read our Guide. Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. ✨ Run & Fine-tune Qwen3 with Unsloth!
Params
—
Context
40,960
Downloads 30d
309 K
Likes
143
Download history
daily snapshots · 10 days320 K309 K
Jul 28Jul 31Aug 3Aug 6
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| Qwen3-8B-Q2_K.gguf | Q2_K | 3.3 GB | 4.1 GB | ✅ Runs comfortably |
| Qwen3-8B-Q2_K_L.gguf | Q2_K_L | 3.4 GB | 4.3 GB | ✅ Runs comfortably |
| Qwen3-8B-Q3_K_S.gguf | Q3_K_S | 3.8 GB | 4.6 GB | ✅ Runs comfortably |
| Qwen3-8B-Q3_K_M.gguf | Q3_K_M | 4.1 GB | 5.0 GB | ✅ Runs comfortably |
| Qwen3-8B-IQ4_XS.gguf | IQ4_XS | 4.6 GB | 5.5 GB | ✅ Runs comfortably |
| Qwen3-8B-IQ4_NL.gguf | IQ4_NL | 4.8 GB | 5.8 GB | ✅ Runs comfortably |
| Qwen3-8B-Q4_1.gguf | Q4_1 | 5.2 GB | 6.3 GB | ✅ Runs comfortably |
| Qwen3-8B-BF16.gguf | GGUF | 16.4 GB | 18.5 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ ollama run qwen3-8b-gguf # pin the quantization explicitly $ ollama run qwen3-8b-gguf-q4_1
$ huggingface-cli download unsloth/Qwen3-8B-GGUF-GGUF \
Qwen3-8B-Q4_1.gguf --local-dir .
$ llama-cli -m Qwen3-8B-Q4_1.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-8b-gguf
{
"hf_id": "unsloth/Qwen3-8B-GGUF",
"params_b": null,
"context_length": 40960,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 308619,
"vram_estimates": [
{ "quant": "GGUF", "gb": 18.5 },
{ "quant": "IQ4_NL", "gb": 5.8 }
],
"updated_at": "2026-07-28T18:06:26Z"
}
Specifications
- Architecture
- Qwen3ForCausalLM
- Context length
- 40,960
- Vocabulary
- 151,936
- Layers / heads
- 36 / 32
- Licence
- apache-2.0
- First seen on the Hub
- 2025-04-28
- Base model
- Qwen3-8B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Sponsored · GPU cloud
Not enough VRAM?
Spin up a 24 GB L4 instance in 40 seconds. $0.44/hr.