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.
DeepSeek V3.2 runs on a 512 GB+ Mac or a multi-GPU server
Best local pick → Mac Studio (M3 Ultra, 512GB) · Q4_K_M · 412.7 GB · ~18 tok/s
Macs from 256 GB (IQ2_M · ~27 tok/s)
Score 110.4#31 of 106 open#27 of 102 that fit ≤512 GBMIT
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
llmrun Composite Score →
110.4
- 90% range 107.4–113.3
- #31 of 106 open models
- #27 of 102 that fit ≤512 GB
Run DeepSeek V3.2
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve deepseek-ai/DeepSeek-V3.2 --max-model-len 16384 --tensor-parallel-size 8Size the nodes from the table above
Download: Q4_K_M/DeepSeek-V3.2-Q4_K_M-00001-of-00009.gguf405.40 GB + 8 partsunsloth
Ways to runOther ways
each opens step-by-stepRun in cloud
Rent 6× H100 SXM · Q4_K_M
- Estimated hourly price
- ~$16.14/hr
- est., whole server
- GPUs
- 6 GPUs
- 480 GB of VRAM
$5+ bonus for new users
How Much VRAM Does DeepSeek V3.2 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 295.2 GB | 293.9 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Runs on 5× H100 SXM 80 GB | |
| 303.7 GB | 302.4 GB | 3-bit small — 3-bit small quantization | Runs on 5× H100 SXM 80 GB | |
| 338.0 GB | 336.7 GB | 3-bit medium — 3-bit medium quantization | Runs on 5× H100 SXM 80 GB | |
| 346.6 GB | 345.3 GB | 4-bit · legacy — 4-bit legacy quantization | Runs on 5× H100 SXM 80 GB | |
| 415.1 GB | 413.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Runs on 6× H100 SXM 80 GB | |
| 492.2 GB | 490.9 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Runs on 7× H100 SXM 80 GB | |
| 569.3 GB | 568 GB | 6-bit, very good — 6-bit quantization, very good quality | Runs on 8× H100 SXM 80 GB | |
| 689.2 GB | 688 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Runs on 6× H200 SXM 141 GB |
Selected Q4_K_M
4-bit medium quantization412.7GBat 16K context
- Weights
- 411.2 GB
- KV cache
- 1.2 GB
- Overhead
- 0.3 GB
Server-class: ~412.7 GB at 16K context · about 6× H100 SXM 80 GB
Which Hardware Can Run DeepSeek V3.2?
Q4_K_M · 415.1 GBDeepSeek 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 7.9 GB, bringing total usage to 423.0 GB. No consumer GPU has enough memory. 1 device with unified memory can run DeepSeek V3.2, including Mac Studio (M3 Ultra, 512GB).
192+ GB
Q4_K_M · best fit IQ2_XXS (189.9 GB)
4 GPUs · 1 Mac class · 2 device families
B300~180Simulate output on B300Instinct MI350X~69Simulate output on Instinct MI350XInstinct MI355X~69Simulate output on Instinct MI355XM3 Ultra256–512 GB~31Simulate output on Mac Studio (M3 Ultra, 256GB)8x H100 SXM5~249Simulate output on NVIDIA DGX H1008x A100 SXM4~225Simulate output on NVIDIA DGX A100 640GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
Consumer GPUs (up to 32 GB) and Macs up to 192 GB: too small for this model (needs ≥ 189.9 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
How good is DeepSeek V3.2?
The llmrun Score merges 13 public benchmark boards into a single figure, where 100 represents the average for open models.
Score vs VRAM in the ≤512 GB tier
- DeepSeek V3.2
- Other models
- Best Score for its VRAM
#27 of 102 that fit ≤512 GB
Each dot is a model at the best quant that fits ≤512 GB. The line steps up to the best Score available at each amount of VRAM; a dot below it is beaten by a model that needs no more memory.
Full ≤512 GB ranking →Benchmarks
The 6 boards that weigh most in the llmrun Score, of 16 with a result for this model; badges show who ran the test.
- SWE-bench Verified
SWE-bench · Feb 2026Independent
Independent70.0%
#5/20 open
- LMArena Text
LMArena · Oct 2026Arena
Arena1424.6
#31/188 open
- Terminal-Bench
Epoch AI · Dec 2025Lab-reported
Lab-reported39.6%
#5/16 open
- LMArena WebDev
LMArena · Oct 2026Arena
Arena1362.5
#36/55 open
- ARC-AGI-2
Epoch AI · Dec 2025Independent
Independent4.0%
#16/22 open
- MMLU-Pro
TIGER-LabIndependent
Independent85.0%
#8/146 open
In the ≤512 GB class
102 models fit ≤512 GBSame Score, only models that fit ≤512 GB at their best quant: this model's peers by memory need.
- #1
DeepSeek V4.1 Flash 1017DeepSeek
134.4
458.4 GB
- #2
MiMo V2.6 Pro RLXiaomi
133.3
499.3 GB
- #3
MiMo V2.6 Flash RLXiaomi
131.9
186.5 GB
- #4
GLM 5.3Z.ai
130.1
453.8 GB
- #5
DeepSeek V4.1 FlashDeepSeek
129.4
458.4 GB
- #6
Step 5 PreviewStepFun
128.0
407.5 GB
Alternatives to DeepSeek V3.2
DeepSeek V3 family · 9 models →Official models with an llmrun Score, each answering one question; sizes are each model's default quant (usually Q4_K_M) with a 16K-token context.
Best alternative at this size
DeepSeek V4.1 Flash 1017
DeepSeek
- 24 higher Score
- 45.8 GB more VRAM
Score 134.4 · 458.4 GB
Fits in less VRAM
GLM 5.3 Flash
Z.ai
- 13.7 higher Score
- 207.5 GB less VRAM
Score 124.1 · 205.2 GB
Other vendor
GLM 5.3
Z.ai
- 19.7 higher Score
- 41.1 GB more VRAM
Score 130.1 · 453.8 GB
Similar models
10| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| DeepSeek V4.1 FlashDeepSeek | 129.4 | 458.4 GB | —needs > 24 GB | similar score |
| Step 5 PreviewStepFun | 128.0 | 407.5 GB | —needs > 24 GB | similar score |
| GLM 5.2Z.ai | 122.9 | 453.8 GB | —needs > 24 GB | similar score |
| Beam 1.0 501B A23Breflection | 119.5 | 304 GB | —needs > 24 GB | similar score |
| GLM 5.1Z.ai | 117.8 | 454.1 GB | —needs > 24 GB | similar score |
| Qwen3.5 397B A17BAlibaba | 112.8 | 242.6 GB | —needs > 24 GB | similar score |
| MiniMax M3MiniMax | 112.6 | 258 GB | —needs > 24 GB | similar score |
| Qwen3.6 27BAlibaba | 111.2 | 17.9 GB | ~38 | similar score |
| GLM 4.7Z.ai | 109.1 | 217.9 GB | —needs > 24 GB | similar score |
| Qwen3 235B A22B Thinking 2507Alibaba | 108.4 | 142.9 GB | —needs > 24 GB | similar score |
Specifications
- Publisher
- DeepSeek
- Family
- DeepSeek V3
- Parameters
- 685.4B
- Active parameters
- 41B per token
- Architecture
- DeepseekV32ForCausalLM
- Context Length
- 163,840 tokens
- Vocabulary Size
- 129,280
- Release Date
- 2025-12-01
- License
- MIT
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 1374.6 GB at BF16. Full 164K context adds up to 7.9 GB (423.0 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)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 11.8 GB (at full 164K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run DeepSeek V3.2?
No — DeepSeek V3.2 requires at least 192.3 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 192.3 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run DeepSeek V3.2 on a Mac?
Yes — Mac Studio (M3 Ultra, 256GB) and 1 other Mac can run DeepSeek V3.2, the smallest at IQ2_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 415.1 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio (M3 Ultra, 512GB).
Can I run DeepSeek V3.2 locally?
Yes — DeepSeek V3.2 can run locally on consumer hardware. 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 411.21 GB. The full-precision BF16 version is 1370.71 GB. The smallest option (IQ2_XXS) is 188.47 GB.
Which GPUs can run DeepSeek V3.2?
No single consumer GPU has enough VRAM to run DeepSeek V3.2 at Q4_K_M (415.1 GB). Multi-GPU or professional hardware is required.
Which devices can run DeepSeek V3.2?
1 device with unified memory can run DeepSeek V3.2 at Q4_K_M (415.1 GB), including Mac Studio (M3 Ultra, 512GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.