Qwen3-Coder-30B-A3B-Instruct-GGUF
See our collection for all versions of Qwen3 including GGUF, 4-bit & 16-bit formats. Learn to run Qwen3-Coder correctly - Read our Guide. See Unsloth Dynamic 2.0 GGUFs for our quantization benchmarks. ✨ Read our Qwen3-Coder Guide here!
Params
—
Context
—
Downloads 30d
4.7 M
Likes
869
Download history
daily snapshots · 10 days4.7 M1.7 M
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-Coder-30B-A3B-Instruct-Q2_K.gguf | Q2_K | 11.3 GB | 12.9 GB | ✅ Runs comfortably |
| Qwen3-Coder-30B-A3B-Instruct-Q2_K_L.gguf | Q2_K_L | 11.3 GB | 13.0 GB | ✅ Runs comfortably |
| Qwen3-Coder-30B-A3B-Instruct-Q3_K_S.gguf | Q3_K_S | 13.3 GB | 15.1 GB | ✅ Runs comfortably |
| Qwen3-Coder-30B-A3B-Instruct-Q3_K_M.gguf | Q3_K_M | 14.7 GB | 16.7 GB | ✅ Runs comfortably |
| Qwen3-Coder-30B-A3B-Instruct-IQ4_XS.gguf | IQ4_XS | 16.4 GB | 18.5 GB | ✅ Runs comfortably |
| Qwen3-Coder-30B-A3B-Instruct-IQ4_NL.gguf | IQ4_NL | 17.3 GB | 19.5 GB | ✅ Runs comfortably |
| Qwen3-Coder-30B-A3B-Instruct-Q4_0.gguf | Q4_0 | 17.4 GB | 19.6 GB | ✅ Runs comfortably |
| Qwen3-Coder-30B-A3B-Instruct-BF16-00001-of-00002.gguf | GGUF | 49.7 GB | 55.1 GB | ❌ Won’t fit |
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-coder-30b-a3b-instruct-gguf # pin the quantization explicitly $ ollama run qwen3-coder-30b-a3b-instruct-gguf-q4_0
$ huggingface-cli download unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF-GGUF \
Qwen3-Coder-30B-A3B-Instruct-Q4_0.gguf --local-dir .
$ llama-cli -m Qwen3-Coder-30B-A3B-Instruct-Q4_0.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-coder-30b-a3b-instruct-gguf
{
"hf_id": "unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 4685368,
"vram_estimates": [
{ "quant": "GGUF", "gb": 55.1 },
{ "quant": "IQ4_NL", "gb": 19.5 }
],
"updated_at": "2026-07-28T18:02:59Z"
}
Specifications
- Licence
- apache-2.0
- First seen on the Hub
- 2025-07-31
- Base model
- Qwen3-Coder-30B-A3B-Instruct
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Family
Base model and the most-downloaded derivatives in the catalog.
Sponsored · GPU cloud
Not enough VRAM?
Spin up a 24 GB L4 instance in 40 seconds. $0.44/hr.