Qwen2.5-Coder-32B-Instruct-GGUF
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:
Params
—
Context
—
Downloads 30d
201 K
Likes
219
Download history
daily snapshots · 10 days215 K201 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 |
|---|---|---|---|---|
| qwen2.5-coder-32b-instruct-fp16-00001-of-00009.gguf | GGUF | 7.8 GB | 9.1 GB | ✅ Runs comfortably |
| qwen2.5-coder-32b-instruct-q2_k.gguf | Q2_K | 12.3 GB | 14.0 GB | ✅ Runs comfortably |
| qwen2.5-coder-32b-instruct-q3_k_m.gguf | Q3_K_M | 15.9 GB | 18.0 GB | ✅ Runs comfortably |
| qwen2.5-coder-32b-instruct-q4_0.gguf | Q4_0 | 18.6 GB | 21.0 GB | ⚠️ Tight — reduce context |
| qwen2.5-coder-32b-instruct-q4_k_m.gguf | Q4_K_M | 19.9 GB | 22.3 GB | ⚠️ Tight — reduce context |
| qwen2.5-coder-32b-instruct-q5_0.gguf | Q5_0 | 22.6 GB | 25.4 GB | ❌ Won’t fit |
| qwen2.5-coder-32b-instruct-q5_k_m.gguf | Q5_K_M | 23.3 GB | 26.1 GB | ❌ Won’t fit |
| qwen2.5-coder-32b-instruct-q6_k.gguf | Q6_K | 26.9 GB | 30.1 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 qwen2-5-coder-32b-instruct-gguf # pin the quantization explicitly $ ollama run qwen2-5-coder-32b-instruct-gguf-q4_0
$ huggingface-cli download Qwen/Qwen2.5-Coder-32B-Instruct-GGUF-GGUF \
qwen2.5-coder-32b-instruct-q4_0.gguf --local-dir .
$ llama-cli -m qwen2.5-coder-32b-instruct-q4_0.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen2-5-coder-32b-instruct-gguf
{
"hf_id": "Qwen/Qwen2.5-Coder-32B-Instruct-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 200507,
"vram_estimates": [
{ "quant": "GGUF", "gb": 9.1 },
{ "quant": "Q2_K", "gb": 14.0 }
],
"updated_at": "2026-07-28T18:08:00Z"
}
Specifications
- Licence
- apache-2.0
- First seen on the Hub
- 2024-11-09
- Base model
- Qwen2.5-Coder-32B-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.