Can NVIDIA GeForce RTX 5090 run DeepSeek V3.2?

No — DeepSeek V3.2 requires at least 192.4 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.

What's the best quantization for DeepSeek V3.2?

For DeepSeek V3.2, Q4_K_M (415.1 GB) offers the best balance of quality and VRAM usage. Q5_K_S (475.1 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 192.4 GB.

Can I run DeepSeek V3.2 on a Mac?

DeepSeek V3.2 requires at least 192.4 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.

Can I run DeepSeek V3.2 locally?

Yes — DeepSeek V3.2 can run locally on consumer hardware. At Q4_K_M quantization it needs 415.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.

What's the download size of DeepSeek V3.2?

At Q4_K_M, the download is about 411.24 GB. The full-precision Q8_0 version is 685.40 GB. The smallest option (IQ2_XXS) is 188.48 GB.

DeepSeek·DeepSeek V3·DeepseekV32ForCausalLM

DeepSeek V3.2 — Hardware Requirements & GPU Compatibility

Chat

DeepSeek V3.2 is the latest iteration of DeepSeek's general-purpose flagship, building on the V3 architecture with 685.4 billion total parameters in a mixture-of-experts configuration. This update refines the model's conversational abilities, instruction following, and multilingual performance compared to earlier V3 releases. Running V3.2 locally requires significant GPU resources due to the large total parameter count, though the MoE design means only a subset of parameters are active for any given token. Users with multi-GPU workstations or servers can run quantized versions effectively, making this one of the most powerful open-weight chat models available for self-hosted deployment.

273.6K downloads 1.3K likesDec 2025164K context

Specifications

Publisher: DeepSeek
Family: DeepSeek V3
Parameters: 685.4B
Architecture: DeepseekV32ForCausalLM
Context Length: 163,840 tokens
Vocabulary Size: 129,280
Release Date: 2025-12-01
License: MIT

Get Started

HuggingFace

deepseek-ai/DeepSeek-V3.2

How Much VRAM Does DeepSeek V3.2 Need?

Select a quantization to see compatible GPUs below.

Quantization	Bits	VRAM	+ Context	File Size	Quality
IQ2_XXS	2.20	192.4 GB	475.3 GB	188.48 GB	Importance-weighted 2-bit, extreme compression — significant quality loss
IQ2_M	2.70	235.2 GB	518.2 GB	231.32 GB	Importance-weighted 2-bit, medium
IQ3_XXS	3.10	269.5 GB	552.5 GB	265.59 GB	Importance-weighted 3-bit
Q2_K	3.40	295.2 GB	578.1 GB	291.29 GB	2-bit quantization with K-quant improvements
Q3_K_S	3.50	303.7 GB	586.7 GB	299.86 GB	3-bit small quantization
Q3_K_M	3.90	338.0 GB	621.0 GB	334.13 GB	3-bit medium quantization
Q4_0	4.00	346.6 GB	629.5 GB	342.70 GB	4-bit legacy quantization
IQ4_XS	4.30	372.3 GB	655.3 GB	368.40 GB	Importance-weighted 4-bit, compact
Q4_1	4.50	389.4 GB	672.4 GB	385.54 GB	4-bit legacy quantization with offset
Q4_K_S	4.50	389.4 GB	672.4 GB	385.54 GB	4-bit small quantization
IQ4_NL	4.50	389.4 GB	672.4 GB	385.54 GB	Importance-weighted 4-bit, non-linear
Q4_K_M	4.80	415.1 GB	698.1 GB	411.24 GB	4-bit medium quantization — most popular sweet spot
Q5_K_S	5.50	475.1 GB	758.1 GB	471.21 GB	5-bit small quantization
Q5_K_M	5.70	492.2 GB	775.2 GB	488.35 GB	5-bit medium quantization — good quality/size tradeoff
Q6_K	6.60	569.3 GB	852.3 GB	565.45 GB	6-bit quantization, very good quality
Q8_0	8.00	689.3 GB	972.3 GB	685.40 GB	8-bit quantization, near-lossless

Which GPUs Can Run DeepSeek V3.2?

Q4_K_M · 415.1 GB

Show professional

DeepSeek V3.2 (Q4_K_M) requires 415.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 540+ GB is recommended. Using the full 164K context window can add up to 283.0 GB, bringing total usage to 698.1 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.

Which Devices Can Run DeepSeek V3.2?

Q4_K_M · 415.1 GB

2 devices with unified memory can run DeepSeek V3.2, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.

Runs great

— Plenty of headroom

NVIDIA DGX H100~42 tok/s NVIDIA DGX A100 640GB~26 tok/s

Related Models

Frequently Asked Questions

How much VRAM does DeepSeek V3.2 need?: DeepSeek V3.2 requires 415.1 GB of VRAM at Q4_K_M, or 689.3 GB at Q8_0. Full 164K context adds up to 283.0 GB (698.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 685.4B × 4.8 bits ÷ 8 = 411.2 GB
KV Cache + Overhead ≈ 3.9 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 286.9 GB (at full 164K context)
VRAM usage by quantization
Q4_K_M
415.1 GB
Q4_K_M + full context
698.1 GB
Learn more about VRAM estimation →
Can NVIDIA GeForce RTX 5090 run DeepSeek V3.2?: No — DeepSeek V3.2 requires at least 192.4 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
What's the best quantization for DeepSeek V3.2?: For DeepSeek V3.2, Q4_K_M (415.1 GB) offers the best balance of quality and VRAM usage. Q5_K_S (475.1 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 192.4 GB.
VRAM requirement by quantization
IQ2_XXS
192.4 GB~53%
Q3_K_S
303.7 GB~77%
Q4_1
389.4 GB~88%
Q4_K_M ★
415.1 GB~89%
Q5_K_S
475.1 GB~92%
Q8_0
689.3 GB~99%
★ Recommended — best balance of quality and VRAM usage.
Learn more about quantization →
Can I run DeepSeek V3.2 on a Mac?: DeepSeek V3.2 requires at least 192.4 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
Can I run DeepSeek V3.2 locally?: Yes — DeepSeek V3.2 can run locally on consumer hardware. At Q4_K_M quantization it needs 415.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of DeepSeek V3.2?: At Q4_K_M, the download is about 411.24 GB. The full-precision Q8_0 version is 685.40 GB. The smallest option (IQ2_XXS) is 188.48 GB.