Qwen3-4B-GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Params
—
Context
—
Downloads 30d
214 K
Likes
7
Download history
daily snapshots · 7 days214 K156 K
Jul 31Aug 2Aug 4Aug 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 |
|---|---|---|---|---|
| Qwen3-4B.Q2_K.gguf | Q2_K | 1.7 GB | 2.3 GB | ✅ Runs comfortably |
| Qwen3-4B.Q3_K_M.gguf | Q3_K_M | 2.1 GB | 2.8 GB | ✅ Runs comfortably |
| Qwen3-4B.Q3_K_L.gguf | Q3_K_L | 2.2 GB | 3.0 GB | ✅ Runs comfortably |
| Qwen3-4B.Q4_K_M.gguf | Q4_K_M | 2.5 GB | 3.2 GB | ✅ Runs comfortably |
| Qwen3-4B.Q5_K_M.gguf | Q5_K_M | 2.9 GB | 3.7 GB | ✅ Runs comfortably |
| Qwen3-4B.Q6_K.gguf | Q6_K | 3.3 GB | 4.1 GB | ✅ Runs comfortably |
| Qwen3-4B.fp16.gguf | GGUF | 8.1 GB | 9.4 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 qwen3-4b-gguf-maziyarpanahi # pin the quantization explicitly $ ollama run qwen3-4b-gguf-maziyarpanahi-q4_k_m
$ huggingface-cli download MaziyarPanahi/Qwen3-4B-GGUF-GGUF \
Qwen3-4B.Q4_K_M.gguf --local-dir .
$ llama-cli -m Qwen3-4B.Q4_K_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-4b-gguf-maziyarpanahi
{
"hf_id": "MaziyarPanahi/Qwen3-4B-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "", "commercial": "unknown" },
"downloads_30d": 213945,
"vram_estimates": [
{ "quant": "Q2_K", "gb": 2.3 },
{ "quant": "Q3_K_L", "gb": 3.0 }
],
"updated_at": "2026-07-31T01:00:46Z"
}
Specifications
- First seen on the Hub
- 2025-04-28
- Base model
- Qwen3-4B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-31
Sponsored · GPU cloud
Not enough VRAM?
Spin up a 24 GB L4 instance in 40 seconds. $0.44/hr.