Qwen3-0.6B-GGUF
MaziyarPanahi/Qwen3-0.6B-GGUF contains GGUF format model files for Qwen/Qwen3-0.6B.
Params
—
Context
—
Downloads 30d
297 K
Likes
15
Download history
daily snapshots · 51 days
▲ 8 K in the last 30 days (2.7%)
299 K260 K
Aug 22Sep 1Sep 11Sep 20
306 K163 K
Aug 1Aug 18Sep 4Sep 20
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 |
|---|---|---|---|---|
| Qwen3-0.6B.Q2_K.gguf | Q2_K | 0.3 GB | 0.9 GB | ✅ Runs comfortably |
| Qwen3-0.6B.Q3_K_L.gguf | Q3_K_L | 0.4 GB | 1.0 GB | ✅ Runs comfortably |
| Qwen3-0.6B.Q3_K_M.gguf | Q3_K_M | 0.4 GB | 1.0 GB | ✅ Runs comfortably |
| Qwen3-0.6B.Q4_K_M.gguf | Q4_K_M | 0.5 GB | 1.0 GB | ✅ Runs comfortably |
| Qwen3-0.6B.Q5_K_M.gguf | Q5_K_M | 0.6 GB | 1.1 GB | ✅ Runs comfortably |
| Qwen3-0.6B.Q6_K.gguf | Q6_K | 0.6 GB | 1.2 GB | ✅ Runs comfortably |
| Qwen3-0.6B.fp16.gguf | GGUF | 1.5 GB | 2.2 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 qwen3-0-6b-gguf # pin the quantization explicitly $ ollama run qwen3-0-6b-gguf-q4_k_m
$ huggingface-cli download MaziyarPanahi/Qwen3-0.6B-GGUF-GGUF \
Qwen3-0.6B.Q4_K_M.gguf --local-dir .
$ llama-cli -m Qwen3-0.6B.Q4_K_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-0-6b-gguf
{
"hf_id": "MaziyarPanahi/Qwen3-0.6B-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "", "commercial": "unknown" },
"downloads_30d": 296565,
"vram_estimates": [
{ "quant": "Q2_K", "gb": 0.9 },
{ "quant": "Q3_K_L", "gb": 1.0 }
],
"updated_at": "2026-08-01T01:00:32Z"
}
Specifications
- First seen on the Hub
- 2025-04-28
- Base model
- Qwen3-0.6B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-01
Compare with any text-generation model