deepseek
14B parameters
Commercial OK
DeepSeek R1 Distill Qwen 14B
14B reasoning distill. Fits on 12GB cards.
License: MIT·Released Jan 20, 2025·Context: 131,072 tokens
Overview
14B reasoning distill. Fits on 12GB cards.
Strengths
- MIT
- Reasoning on 12GB
Weaknesses
- Reasoning quality below 32B distill
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 8.4 GB | 11 GB |
Get the model
Ollama
One-line install
ollama run deepseek-r1:14bRead our Ollama review →HuggingFace
Original weights
huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Source repository — direct quantization required.
Hardware that runs this
Cards with enough VRAM for at least one quantization of DeepSeek R1 Distill Qwen 14B.
Compare alternatives
Models worth comparing
Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.
Same tier
Models in the same parameter band as this one
Step up
More capable — bigger memory footprint
Step down
Smaller — faster, runs on weaker hardware
Frequently asked
What's the minimum VRAM to run DeepSeek R1 Distill Qwen 14B?
11GB of VRAM is enough to run DeepSeek R1 Distill Qwen 14B at the Q4_K_M quantization (file size 8.4 GB). Higher-quality quantizations need more.
Can I use DeepSeek R1 Distill Qwen 14B commercially?
Yes — DeepSeek R1 Distill Qwen 14B ships under the MIT, which permits commercial use. Always read the license text before deployment.
What's the context length of DeepSeek R1 Distill Qwen 14B?
DeepSeek R1 Distill Qwen 14B supports a context window of 131,072 tokens (about 131K).
How do I install DeepSeek R1 Distill Qwen 14B with Ollama?
Run `ollama pull deepseek-r1:14b` to download, then `ollama run deepseek-r1:14b` to start a chat session. The default quantization is Q4_K_M.
Source: huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.