Check my GPU

on

Can the NVIDIA GeForce RTX 3090 run DeepSeek Coder V2 Lite (16B)?

78 ptsGreat (A) · 78 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15

Yes, it runs well

Runs well. At Q8_0 it needs about 18.7 GB of 24.0 GB usable, with an estimated speed of 122 tok/s.

Best quant
Q8_0
Generation speed
122 tok/s
Prompt processing
10,680 tok/s
First token (1K prompt)
0.3 s
Largest safe context
160K

Download DeepSeek Coder V2 Lite (16B)

Recommended for the NVIDIA GeForce RTX 3090: Q8_0. 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-coder-v2:16b-lite-instruct-q8_0

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 Q8_0 file (opens in a new tab)

huggingface.co/lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF (opens in a new tab)

ollama run hf.co/lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q8_0

Original weights · Hugging Face

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

huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct (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-Coder-V2 (opens in a new tab)

git clone https://github.com/deepseek-ai/DeepSeek-Coder-V2

Links checked 7 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.23.4 / 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.15.0 / 15
Total78.4 / 10078 ptsGreat (A) · 78 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15

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

Every quantization on the NVIDIA GeForce RTX 3090

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 8.3 GB 24.0 GB 393 tok/s Runs well 64 ptsGood (B) · 64 of 100 points: Model quality 16.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.0/15
Q3_K_M 9.8 GB 24.0 GB 309 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.4/15 GGUF (Q3_K_L) (opens in a new tab)
Q4_K_M 11.6 GB 24.0 GB 239 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15 GGUF (opens in a new tab)
Q5_K_M 13.2 GB 24.0 GB 198 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 22.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.7/15 GGUF (opens in a new tab)
Q6_K 14.9 GB 24.0 GB 166 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 23.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.4/15 GGUF (opens in a new tab)
Q8_0 18.7 GB 24.0 GB 122 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF (opens in a new tab)
F16 33.5 GB 24.0 GB 11.4 tok/s Heavy offload 50 ptsUsable (C) · 50 of 100 points: Model quality 23.4/45, Memory fit 4.0/25, Speed 8.0/15, Memory use 15.0/15 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.