Skip to content
localmodel.run

Text model · DeepSeek-R1-Distill

DeepSeek-R1-Distill-Qwen 7B requirements

DeepSeek-R1-Distill family · 7B params · released Jan 2025 · 79.3M Ollama pulls. Minimum to run at Q4_K_M: Nvidia GeForce RTX 3060 (12GB).

LicenseMIT· Commercial OK↓ 329.2K/mo♥ 842on HuggingFace
Q4_K_M
4.68 GB
Q8_0
8.1 GB
Total @ Q4 (4k)
~6.1 GB
Context
128 k

Quantization sizes

GGUF quantson disk
QuantizationSize on disk
Q2_K2.9 GB est
Q3_K_M3.4 GB est
Q4_K_M (default)4.68 GB
Q5_K_M5 GB est
Q6_K5.7 GB est
Q8_08.1 GB
FP1614 GB est

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run deepseek-r1:7b
llama.cpp
$ llama-cli -hf bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M
LM Studio
$ lms get bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF

Which devices can run DeepSeek-R1-Distill-Qwen 7B?

FAQ

How much VRAM or RAM does DeepSeek-R1-Distill-Qwen 7B need?

At Q4_K_M, DeepSeek-R1-Distill-Qwen 7B needs about 6.1 GB (weights ~4.68 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~9.5 GB.

Can DeepSeek-R1-Distill-Qwen 7B run on a laptop?

Yes, DeepSeek-R1-Distill-Qwen 7B fits on a 16 GB machine at Q4_K_M and runs on Apple Silicon or a 12 GB+ GPU comfortably.

Can I use DeepSeek-R1-Distill-Qwen 7B commercially?

Yes. DeepSeek-R1-Distill-Qwen 7B is licensed MIT, which permits commercial use.

Distilled from DeepSeek-R1 onto Qwen2.5-7B base. Released 2025-01-20. Q4_K_M=4.68GB, Q8_0=8.10GB from bartowski HF repo. Ollama shows 4.7GB. Context 128K.

Sources

Memory figures are estimates. See methodology.