Yes — with 13.1 GB to spare

DeepSeek-R1-Distill-Qwen 7B at Q4_K_M fits your RTX 4000 Ada entirely on the GPU at 8K context, at an estimated 51 tokens per second. There is room for its full 128K window.

Fully on GPU 8K context Q4_K_M · 4.3 GB MIT Released Jan 2025

Reasoning traces on a 7B budget. Expect long outputs — budget context accordingly.

What hardware do I need for DeepSeek-R1-Distill-Qwen 7B? →

The VRAM budget

weights 4.3 GB

Weights 4.3 GB KV cache @ 8K 0.44 GB Runtime overhead 0.6 GB Free 13.1 GB of 18.4 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
F16	14.2 GB	15.2 GB	65K	15	Reference	Long context
Q8_0	7.5 GB	8.6 GB	128K	29	−0.1% ppl	Long context
Q6_K	5.8 GB	6.9 GB	128K	37	−0.4% ppl	Long context
Q5_K_M	5.0 GB	6.1 GB	128K	43	−0.8% ppl	Long context
Q4_K_M	4.3 GB	5.3 GB	128K	51	−1.9% ppl	Recommended
Q3_K_M	3.5 GB	4.5 GB	128K	63	−5.4% ppl	Long context
Q2_K	3.0 GB	4.0 GB	128K	73	−15% ppl	Long context

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.

How to run it

Ollama llama.cpp LM Studio vLLM

terminal

$ ollama pull deepseek-r1:7b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run deepseek-r1:7b

The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.

01Download is 4.3 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.

02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.

03There is room to go to the model's full 128K context on this card.

See all models for this rig Compare with another model