DeepSeek-R1-Distill-Qwen-7B-GGUF
Filename Quant type File Size Split Description -------- ---------- --------- ----- ----------- DeepSeek-R1-Distill-Qwen-7B-f32.gguf f32 30.47GB false Full F32 weights. DeepSeek-R1-Distill-Qwen-7B-f16.gguf f16 15.24GB false Full F16 weights. DeepSeek-R1-Distill-Qwen-7B-Q80.gguf Q80 8.10GB false Extremely high quality, generally unneeded but max available quant. DeepSeek-R1-Distill-Qwen-7B-Q6KL.gguf Q6KL 6.52GB false...
Params
7.0 B
Context
131,072
Downloads 30d
139 K
Likes
149
Download history
tracking started — chart appears after 7 days of snapshots (6 recorded)139 K downloads in the last 30 days
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 |
|---|---|---|---|---|
| DeepSeek-R1-Distill-Qwen-7B-IQ2_M.gguf | IQ2_M | 2.8 GB | 4.6 GB | ✅ Runs comfortably |
| DeepSeek-R1-Distill-Qwen-7B-Q2_K.gguf | Q2_K | 3.0 GB | 4.9 GB | ✅ Runs comfortably |
| DeepSeek-R1-Distill-Qwen-7B-IQ3_XS.gguf | IQ3_XS | 3.3 GB | 5.2 GB | ✅ Runs comfortably |
| DeepSeek-R1-Distill-Qwen-7B-IQ3_M.gguf | IQ3_M | 3.6 GB | 5.5 GB | ✅ Runs comfortably |
| DeepSeek-R1-Distill-Qwen-7B-Q2_K_L.gguf | Q2_K_L | 3.5 GB | 5.5 GB | ✅ Runs comfortably |
| DeepSeek-R1-Distill-Qwen-7B-Q3_K_L.gguf | Q3_K_L | 4.1 GB | 6.0 GB | ✅ Runs comfortably |
| DeepSeek-R1-Distill-Qwen-7B-IQ4_XS.gguf | IQ4_XS | 4.2 GB | 6.2 GB | ✅ Runs comfortably |
| DeepSeek-R1-Distill-Qwen-7B-IQ4_NL.gguf | IQ4_NL | 4.4 GB | 6.4 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 deepseek-r1-distill-qwen-7b-gguf # pin the quantization explicitly $ ollama run deepseek-r1-distill-qwen-7b-gguf-iq2_m
$ huggingface-cli download bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF-GGUF \
DeepSeek-R1-Distill-Qwen-7B-IQ2_M.gguf --local-dir .
$ llama-cli -m DeepSeek-R1-Distill-Qwen-7B-IQ2_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/deepseek-r1-distill-qwen-7b-gguf
{
"hf_id": "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF",
"params_b": 7.00,
"context_length": 131072,
"license": { "id": "", "commercial": "unknown" },
"downloads_30d": 139322,
"vram_estimates": [
{ "quant": "IQ2_M", "gb": 4.6 },
{ "quant": "IQ3_M", "gb": 5.5 }
],
"updated_at": "2026-11-05T01:00:40Z"
}
Specifications
- Parameters
- 7.0 B
- Context length
- 131,072
- First seen on the Hub
- 2025-01-20
- Base model
- DeepSeek-R1-Distill-Qwen-7B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-11-05
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model