Check my GPU

on

Can the NVIDIA GeForce RTX 5090 run DeepSeek R1 Distill Llama 8B?

76 ptsGreat (A) · 76 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.9/15

Yes, it runs well

Runs well. At F16 it needs about 19.3 GB of 32.0 GB usable, with an estimated speed of 64.3 tok/s.

Best quant
F16
Generation speed
64.3 tok/s
Prompt processing
9,397 tok/s
First token (1K prompt)
0.3 s
Largest safe context
102K

Download DeepSeek R1 Distill Llama 8B

Recommended for the NVIDIA GeForce RTX 5090: F16. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run deepseek-r1:8b-llama-distill-fp16

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the F16 file (opens in a new tab)

huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF:BF16

Original weights · Hugging Face

Full-precision files from DeepSeek, for fine-tuning, vLLM, Transformers.

huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from DeepSeek. The weights themselves download from Hugging Face.

github.com/deepseek-ai/DeepSeek-R1 (opens in a new tab)

git clone https://github.com/deepseek-ai/DeepSeek-R1

The R1 repo covers the distilled models too.

Links checked 6 days ago against Hugging Face, Ollama and GitHub.

How the A grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.22.5 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.13.9 / 15
Total76.4 / 10076 ptsGreat (A) · 76 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.9/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the NVIDIA GeForce RTX 5090

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 6.5 GB 32.0 GB 450 tok/s Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.7/15 GGUF (opens in a new tab)
Q3_K_M 7.2 GB 32.0 GB 354 tok/s Runs well 64 ptsGood (B) · 64 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.2/15 GGUF (opens in a new tab)
Q4_K_M 8.2 GB 32.0 GB 274 tok/s Runs well 67 ptsGood (B) · 67 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15 GGUF (opens in a new tab)
Q5_K_M 9.0 GB 32.0 GB 226 tok/s Runs well 68 ptsGood (B) · 68 of 100 points: Model quality 21.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.5/15 GGUF (opens in a new tab)
Q6_K 9.9 GB 32.0 GB 190 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 22.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.1/15 GGUF (opens in a new tab)
Q8_0 11.8 GB 32.0 GB 139 tok/s Runs well 70 ptsGood (B) · 70 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.5/15 GGUF (opens in a new tab)
F16 19.3 GB 32.0 GB 64.3 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.9/15 GGUF (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.