Qwen_Qwen3-4B-GGUF
Filename Quant type File Size Split Description -------- ---------- --------- ----- ----------- Qwen3-4B-bf16.gguf bf16 8.05GB false Full BF16 weights. Qwen3-4B-Q80.gguf Q80 4.28GB false Extremely high quality, generally unneeded but max available quant. Qwen3-4B-Q6KL.gguf Q6KL 3.40GB false Uses Q80 for embed and output weights. Very high quality, near perfect, recommended. Qwen3-4B-Q6K.gguf Q6K 3.31GB false Very hig...
Params
4.0 B
Context
40,960
Downloads 30d
245 K
Likes
22
Download history
daily snapshots · 19 days246 K192 K
Oct 6Oct 12Oct 18Oct 24
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 |
|---|---|---|---|---|
| Qwen_Qwen3-4B-IQ2_M.gguf | IQ2_M | 1.5 GB | 2.8 GB | ✅ Runs comfortably |
| Qwen_Qwen3-4B-IQ3_XXS.gguf | IQ3_XXS | 1.7 GB | 2.9 GB | ✅ Runs comfortably |
| Qwen_Qwen3-4B-Q2_K.gguf | Q2_K | 1.7 GB | 2.9 GB | ✅ Runs comfortably |
| Qwen_Qwen3-4B-Q2_K_L.gguf | Q2_K_L | 1.8 GB | 3.0 GB | ✅ Runs comfortably |
| Qwen_Qwen3-4B-IQ3_XS.gguf | IQ3_XS | 1.8 GB | 3.1 GB | ✅ Runs comfortably |
| Qwen_Qwen3-4B-IQ3_M.gguf | IQ3_M | 2.0 GB | 3.3 GB | ✅ Runs comfortably |
| Qwen_Qwen3-4B-IQ4_XS.gguf | IQ4_XS | 2.3 GB | 3.6 GB | ✅ Runs comfortably |
| Qwen_Qwen3-4B-IQ4_NL.gguf | IQ4_NL | 2.4 GB | 3.7 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 qwen-qwen3-4b-gguf # pin the quantization explicitly $ ollama run qwen-qwen3-4b-gguf-iq2_m
$ huggingface-cli download bartowski/Qwen_Qwen3-4B-GGUF-GGUF \
Qwen_Qwen3-4B-IQ2_M.gguf --local-dir .
$ llama-cli -m Qwen_Qwen3-4B-IQ2_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen-qwen3-4b-gguf
{
"hf_id": "bartowski/Qwen_Qwen3-4B-GGUF",
"params_b": 4.00,
"context_length": 40960,
"license": { "id": "", "commercial": "unknown" },
"downloads_30d": 245245,
"vram_estimates": [
{ "quant": "IQ2_M", "gb": 2.8 },
{ "quant": "IQ3_M", "gb": 3.3 }
],
"updated_at": "2026-10-06T01:00:15Z"
}
Specifications
- Parameters
- 4.0 B
- Context length
- 40,960
- First seen on the Hub
- 2025-04-28
- Base model
- Qwen3-4B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-06
Compare with any text-generation model