DeepSeek Coder V2 (236B) on NVIDIA GeForce RTX 4090

Can the NVIDIA GeForce RTX 4090 run DeepSeek Coder V2 (236B)?

6 pts

No, it doesn’t fit

No. DeepSeek Coder V2 (236B) needs about 96.7 GB even at Q2_K; the NVIDIA GeForce RTX 4090 has 24.0 GB usable.

Download DeepSeek Coder V2 (236B)

Recommended: Q2_K. 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-v2:236b-instruct-q2_K

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.

huggingface.co/lmstudio-community/DeepSeek-Coder-V2-Instruct-0724-GGUF (opens in a new tab)

ollama run hf.co/lmstudio-community/DeepSeek-Coder-V2-Instruct-0724-GGUF

Original weights · Hugging Face

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

huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct-0724 (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 5 days ago against Hugging Face, Ollama and GitHub.

How the F 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.	7.0 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	0.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	0.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	0.0 / 15
Total	7.0 / 100	6 ptsWon't run (F) · 6 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15

It doesn’t fit, so only a reduced share of the quality points counts and fit, speed and memory use score zero.

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

Every quantization on the NVIDIA GeForce RTX 4090

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	96.7 GB	24.0 GB	—	Won't run	6 ptsWon't run (F) · 6 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15
`Q3_K_M`	118 GB	24.0 GB	—	Won't run	8 ptsWon't run (F) · 8 of 100 points: Model quality 8.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (Q3_K_L) · part 1 of 4 (opens in a new tab)
`Q4_K_M`	146 GB	24.0 GB	—	Won't run	9 ptsWon't run (F) · 9 of 100 points: Model quality 9.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF · part 1 of 4 (opens in a new tab)
`Q5_K_M`	170 GB	24.0 GB	—	Won't run	9 ptsWon't run (F) · 9 of 100 points: Model quality 9.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15
`Q6_K`	196 GB	24.0 GB	—	Won't run	9 ptsWon't run (F) · 9 of 100 points: Model quality 9.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF · part 1 of 5 (opens in a new tab)
`Q8_0`	252 GB	24.0 GB	—	Won't run	9 ptsWon't run (F) · 9 of 100 points: Model quality 10.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF · part 1 of 7 (opens in a new tab)
`F16`	474 GB	24.0 GB	—	Won't run	9 ptsWon't run (F) · 9 of 100 points: Model quality 10.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Original weights (opens in a new tab)

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

Hardware that can run it

82 ptsGreat (A) · 82 of 100 points: Model quality 31.6/45, Memory fit 25.0/25, Speed 10.8/15, Memory use 15.0/15 Apple M3 Ultra (256 GB) Q4_K_M · 20.6 tok/s
79 ptsGreat (A) · 79 of 100 points: Model quality 28.0/45, Memory fit 24.0/25, Speed 12.1/15, Memory use 15.0/15 Apple M2 Ultra (192 GB) Q3_K_M · 26.0 tok/s
77 ptsGreat (A) · 77 of 100 points: Model quality 31.6/45, Memory fit 25.0/25, Speed 10.8/15, Memory use 10.6/15 Apple M3 Ultra (512 GB) Q4_K_M · 20.6 tok/s
70 ptsGood (B) · 70 of 100 points: Model quality 23.3/45, Memory fit 24.0/25, Speed 8.6/15, Memory use 15.0/15 NVIDIA GB10 (128 GB) Q2_K · 13.1 tok/s
63 ptsGood (B) · 63 of 100 points: Model quality 23.3/45, Memory fit 10.0/25, Speed 14.9/15, Memory use 15.0/15 NVIDIA RTX PRO 6000 Blackwell Q2_K · 39.6 tok/s
58 ptsGood (B) · 58 of 100 points: Model quality 23.3/45, Memory fit 10.0/25, Speed 10.4/15, Memory use 15.0/15 Apple M4 Max (128 GB) Q2_K · 19.2 tok/s

Models that do run on the NVIDIA GeForce RTX 4090

95 ptsExcellent (S) · 95 of 100 points: Model quality 40.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Qwen3.8 27B Q4_K_M · 44.5 tok/s
95 ptsExcellent (S) · 95 of 100 points: Model quality 41.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Gemma 4 26B-A4B Q6_K · 113 tok/s
95 ptsExcellent (S) · 95 of 100 points: Model quality 40.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Qwen3.6 27B Q4_K_M · 44.5 tok/s
94 ptsExcellent (S) · 94 of 100 points: Model quality 39.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Qwen3.5 27B Q4_K_M · 44.5 tok/s
93 ptsExcellent (S) · 93 of 100 points: Model quality 40.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Qwen3.6 35B-A3B Q4_K_M · 206 tok/s

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.