Qwen2.5-7B-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
7.0 B
Context
32,768
Downloads 30d
187 K
Likes
200
Download history
daily snapshots · 11 days187 K170 K
Oct 15Oct 18Oct 22Oct 25
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 |
|---|---|---|---|---|
| qwen2.5-7b-instruct-q2_k.gguf | Q2_K | 3.0 GB | 4.9 GB | ✅ Runs comfortably |
| qwen2.5-7b-instruct-q3_k_m.gguf | Q3_K_M | 3.8 GB | 5.7 GB | ✅ Runs comfortably |
| qwen2.5-7b-instruct-fp16-00001-of-00004.gguf | GGUF | 4.0 GB | 5.9 GB | ✅ Runs comfortably |
| qwen2.5-7b-instruct-q4_0-00001-of-00002.gguf | Q4_0 | 4.0 GB | 5.9 GB | ✅ Runs comfortably |
| qwen2.5-7b-instruct-q4_k_m-00001-of-00002.gguf | Q4_K_M | 4.0 GB | 5.9 GB | ✅ Runs comfortably |
| qwen2.5-7b-instruct-q5_k_m-00001-of-00002.gguf | Q5_K_M | 4.0 GB | 5.9 GB | ✅ Runs comfortably |
| qwen2.5-7b-instruct-q6_k-00001-of-00002.gguf | Q6_K | 4.0 GB | 5.9 GB | ✅ Runs comfortably |
| qwen2.5-7b-instruct-q5_0-00001-of-00002.gguf | Q5_0 | 4.0 GB | 6.0 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 qwen2-5-7b-instruct-gguf-qwen # pin the quantization explicitly $ ollama run qwen2-5-7b-instruct-gguf-qwen-q4_0
$ huggingface-cli download Qwen/Qwen2.5-7B-Instruct-GGUF-GGUF \
qwen2.5-7b-instruct-q4_0-00001-of-00002.gguf --local-dir .
$ llama-cli -m qwen2.5-7b-instruct-q4_0-00001-of-00002.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen2-5-7b-instruct-gguf-qwen
{
"hf_id": "Qwen/Qwen2.5-7B-Instruct-GGUF",
"params_b": 7.00,
"context_length": 32768,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 187040,
"vram_estimates": [
{ "quant": "GGUF", "gb": 5.9 },
{ "quant": "Q2_K", "gb": 4.9 }
],
"updated_at": "2026-10-15T01:00:28Z"
}
Specifications
- Parameters
- 7.0 B
- Context length
- 32,768
- Licence
- apache-2.0
- First seen on the Hub
- 2024-09-17
- Base model
- Qwen2.5-7B-Instruct
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-15
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model