Skip to content

How much VRAM does DeepSeek V3.2 need?

DeepSeek V3.2 needs 379 GB for its weights at 4-bit, 380 GB with an 8K context and 382 GB with 32K.

Parameters
671B
Active per token
37B
Longest context
160K
Released
Dec 2025
License
MIT
Strongest at
Chat, Coding, Agents, Docs

Memory at each precision

Memory DeepSeek V3.2 needs at each precision and context length
PrecisionWeightsWith 8KWith 32KWith 128K
As released (FP8)642 GB644 GB645 GB653 GB
6-bit512 GB514 GB516 GB523 GB
5-bit444 GB446 GB448 GB455 GB
4-bit379 GB380 GB382 GB389 GB
3-bit305 GB307 GB309 GB316 GB
2-bit234 GB236 GB238 GB245 GB
1.6-bit129 GB130 GB132 GB139 GB

One conversation, 16-bit context cache, runtime overhead included.

What runs it

The best way DeepSeek V3.2 runs on common GPUs, Macs and AI boxes
MachineBest fitContextSpeedFirst reply
RTX 3060 12 GBToo big
RTX 4060 Ti 16 GBToo big
RTX 3090Too big
RTX 4090Too big
RTX 5090Too big
2× RTX 3090Too big
RTX PRO 6000 BlackwellToo big
M4 Max 128 GBToo big
M5 Max 128 GBToo big
Ryzen AI Max+ 395 128 GBToo big
DGX Spark 128 GBToo big
M3 Ultra 256 GB1.6-bit160K44 tok/s23 s
M5 Ultra 512 GB3-bit160K32 tok/s7.2 s
H100 SXMToo big
DGX Station GB3002-bit52K155 tok/s0.7 s
8× H200 NVLFP8160K67 tok/s0.3 s

Best fit is the highest quality, up to 8-bit, that leaves 16K of context. First reply is the wait for a 2K prompt. Speeds are rough, plus or minus 25%.

How to run it

llama.cpp
llama-server -hf unsloth/DeepSeek-V3.2-GGUF
vLLM
vllm serve deepseek-ai/DeepSeek-V3.2
MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-V3.2-4bit

Questions

How much VRAM does DeepSeek V3.2 need?

DeepSeek V3.2 needs 379 GB for its weights at 4-bit, 380 GB with an 8K context and 382 GB with 32K.

Can DeepSeek V3.2 run on an RTX 4090?

Not on one card. The smallest machine here that runs it is the M3 Ultra 256 GB.

More models