Qwen2.5-3B-Instruct-GGUF
Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:
Params
—
Context
—
Downloads 30d
189 K
Likes
157
Download history
daily snapshots · 10 days191 K184 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 |
|---|---|---|---|---|
| qwen2.5-3b-instruct-q2_k.gguf | Q2_K | 1.4 GB | 2.0 GB | ✅ Runs comfortably |
| qwen2.5-3b-instruct-q3_k_m.gguf | Q3_K_M | 1.7 GB | 2.4 GB | ✅ Runs comfortably |
| qwen2.5-3b-instruct-q4_0.gguf | Q4_0 | 2.0 GB | 2.7 GB | ✅ Runs comfortably |
| qwen2.5-3b-instruct-q4_k_m.gguf | Q4_K_M | 2.1 GB | 2.8 GB | ✅ Runs comfortably |
| qwen2.5-3b-instruct-q5_0.gguf | Q5_0 | 2.4 GB | 3.1 GB | ✅ Runs comfortably |
| qwen2.5-3b-instruct-q5_k_m.gguf | Q5_K_M | 2.4 GB | 3.2 GB | ✅ Runs comfortably |
| qwen2.5-3b-instruct-q6_k.gguf | Q6_K | 2.8 GB | 3.6 GB | ✅ Runs comfortably |
| qwen2.5-3b-instruct-fp16-00001-of-00002.gguf | GGUF | 4.0 GB | 4.9 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 qwen2-5-3b-instruct-gguf # pin the quantization explicitly $ ollama run qwen2-5-3b-instruct-gguf-q4_0
$ huggingface-cli download Qwen/Qwen2.5-3B-Instruct-GGUF-GGUF \
qwen2.5-3b-instruct-q4_0.gguf --local-dir .
$ llama-cli -m qwen2.5-3b-instruct-q4_0.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen2-5-3b-instruct-gguf
{
"hf_id": "Qwen/Qwen2.5-3B-Instruct-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 188869,
"vram_estimates": [
{ "quant": "GGUF", "gb": 4.9 },
{ "quant": "Q2_K", "gb": 2.0 }
],
"updated_at": "2026-07-28T18:08:27Z"
}
Specifications
- Licence
- other
- First seen on the Hub
- 2024-09-17
- Base model
- Qwen2.5-3B-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.