Qwen2.5-32B-Instruct-GGUF
Filename Quant type File Size Split Description -------- ---------- --------- ----- ----------- Qwen2.5-32B-Instruct-f16.gguf f16 65.54GB true Full F16 weights. Qwen2.5-32B-Instruct-Q80.gguf Q80 34.82GB false Extremely high quality, generally unneeded but max available quant. Qwen2.5-32B-Instruct-Q6KL.gguf Q6KL 27.26GB false Uses Q80 for embed and output weights. Very high quality, near perfect, recommended. Qwen2.5-...
Params
32.0 B
Context
32,768
Downloads 30d
955 K
Likes
90
Download history
daily snapshots · 28 days999 K189 K
Sep 27Oct 6Oct 15Oct 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 |
|---|---|---|---|---|
| Qwen2.5-32B-Instruct-IQ2_XXS.gguf | IQ2_XXS | 9.0 GB | 15.2 GB | ✅ Runs comfortably |
| Qwen2.5-32B-Instruct-IQ2_XS.gguf | IQ2_XS | 10.0 GB | 16.3 GB | ✅ Runs comfortably |
| Qwen2.5-32B-Instruct-IQ2_S.gguf | IQ2_S | 10.4 GB | 16.7 GB | ✅ Runs comfortably |
| Qwen2.5-32B-Instruct-IQ2_M.gguf | IQ2_M | 11.3 GB | 17.7 GB | ✅ Runs comfortably |
| Qwen2.5-32B-Instruct-Q2_K.gguf | Q2_K | 12.3 GB | 18.8 GB | ✅ Runs comfortably |
| Qwen2.5-32B-Instruct-IQ3_XS.gguf | IQ3_XS | 13.7 GB | 20.4 GB | ⚠️ Tight — reduce context |
| Qwen2.5-32B-Instruct-IQ3_M.gguf | IQ3_M | 14.8 GB | 21.6 GB | ⚠️ Tight — reduce context |
| Qwen2.5-32B-Instruct-IQ4_XS.gguf | IQ4_XS | 17.7 GB | 24.8 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 qwen2-5-32b-instruct-gguf # pin the quantization explicitly $ ollama run qwen2-5-32b-instruct-gguf-iq2_m
$ huggingface-cli download bartowski/Qwen2.5-32B-Instruct-GGUF-GGUF \
Qwen2.5-32B-Instruct-IQ2_M.gguf --local-dir .
$ llama-cli -m Qwen2.5-32B-Instruct-IQ2_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen2-5-32b-instruct-gguf
{
"hf_id": "bartowski/Qwen2.5-32B-Instruct-GGUF",
"params_b": 32.00,
"context_length": 32768,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 954609,
"vram_estimates": [
{ "quant": "IQ2_M", "gb": 17.7 },
{ "quant": "IQ2_S", "gb": 16.7 }
],
"updated_at": "2026-09-27T01:00:27Z"
}
Specifications
- Parameters
- 32.0 B
- Context length
- 32,768
- Licence
- apache-2.0
- First seen on the Hub
- 2024-09-17
- Base model
- Qwen2.5-32B-Instruct
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-27
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model