DeepSeek V3.2 Exp — Hardware Requirements & GPU Compatibility
ChatFunctions
DeepSeek-V3.2-Exp is an experimental release from DeepSeek that introduces DeepSeek Sparse Attention, a fine-grained sparse attention mechanism meant to improve training and inference efficiency for long-context work. It is a Mixture-of-Experts model at roughly 685 billion total parameters, fine-tuned from a matching V3.2-Exp base checkpoint, and it retains the general reasoning, coding, and agentic tool-use capabilities of DeepSeek's earlier V3.1-Terminus release while testing whether sparse attention can match that quality more efficiently. It supports a 160K token context window and is released under the MIT license. At roughly 685 billion total parameters, even 4-bit quantization needs several hundred gigabytes of memory, so realistic local use means multi-GPU server hardware; most users will rely on a hosted endpoint instead.
DeepSeek V3.2 Exp 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 512 GB (Q4_K_M · ~18 tok/s)
Score 109#35 of 106 open#31 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 →
109.0
- 90% range 104.6–113.5
- #35 of 106 open models
- #31 of 102 that fit ≤512 GB
Run DeepSeek V3.2 Exp
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-Exp --max-model-len 16384 --tensor-parallel-size 8Size the nodes from the table above
Download: Weights on Hugging Face
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 Exp 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 | |
| 338.0 GB | 336.7 GB | 3-bit medium — 3-bit medium 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 | 491 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Runs on 7× H100 SXM 80 GB | |
| 569.3 GB | 568.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Runs on 8× H100 SXM 80 GB | |
| 689.3 GB | 688 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Runs on 6× H200 SXM 141 GB | |
| 1374.7 GB | 1373.4 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on 8× B200 192 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 Exp?
Q4_K_M · 415.1 GBDeepSeek V3.2 Exp (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 423.1 GB. No consumer GPU has enough memory. 1 device with unified memory can run DeepSeek V3.2 Exp, including Mac Studio (M3 Ultra, 512GB).
Needs server-class hardware
DeepSeek V3.2 Exp runs on a 512 GB+ Mac or a multi-GPU server · Q4_K_M needs ~412.7 GB
| Hardware | Quant | Memory | Speed | Context | Hardware page | |
|---|---|---|---|---|---|---|
| Mac 512 GB · Mac Studio (M3 Ultra, 512GB) | Q4_K_M | 412.7 GB | ~18 tok/s | 160K ctx | Mac Studio → | Q4_K_M · 412.7 GB · ~18 tok/s · 160K ctx |
| 6× H100 SXM 80 GB · 480 GB | Q4_K_M | 412.7 GB | — | 160K ctx | H100 SXM → | Q4_K_M · 412.7 GB · 160K ctx |
| 4× H200 SXM 141 GB · 564 GB | Q4_K_M | 412.7 GB | — | 160K ctx | H200 SXM → | Q4_K_M · 412.7 GB · 160K ctx |
| 3× B200 192 GB · 576 GB | Q4_K_M | 412.7 GB | — | 160K ctx | B200 → | Q4_K_M · 412.7 GB · 160K ctx |
Also: Mac Studio (M3 Ultra, 512GB) · NVIDIA DGX A100 640GB · NVIDIA DGX H100
By VRAM tier · typical GPUs and Macs at Q4_K_M
Consumer GPUs (up to 32 GB) and Macs up to 256 GB: too small for this model (needs ≥ 292.8 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
How good is DeepSeek V3.2 Exp?
The llmrun Score merges 10 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 Exp
- Other models
- Best Score for its VRAM
#31 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 12 with a result for this model; badges show who ran the test.
- LMArena Text
LMArena · Oct 2026Arena
Arena1425.1
#29/188 open
- LMArena WebDev
LMArena · Oct 2026Arena
Arena1271.4
#49/55 open
- Aider Polyglot
Epoch AI · Sep 2025Independent
Independent74.2%
#1/18 open
- SciCode
Epoch AI · Sep 2025Lab-reported
Lab-reported38.9%
#40/72 open
- WeirdML
Epoch AI · Sep 2025Independent
Independent39.5%
#25/47 open
- CritPt
Epoch AI · Sep 2025Lab-reported
Lab-reported2.9%
#30/84 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 Exp
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
- 25.4 higher Score
- 45.7 GB more VRAM
Score 134.4 · 458.4 GB
Fits in less VRAM
GLM 5.3 Flash
Z.ai
- 15.1 higher Score
- 207.5 GB less VRAM
Score 124.1 · 205.2 GB
Other vendor
GLM 5.3
Z.ai
- 21.1 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
- 2025-09-29
- License
- MIT
Frequently Asked Questions
How much VRAM does DeepSeek V3.2 Exp need?
DeepSeek V3.2 Exp requires 415.1 GB of VRAM at Q4_K_M, or 1374.7 GB at BF16. Full 164K context adds up to 7.9 GB (423.1 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)
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 ≈ 11.9 GB (at full 164K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run DeepSeek V3.2 Exp?
No — DeepSeek V3.2 Exp requires at least 295.2 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
What's the best quantization for DeepSeek V3.2 Exp?
For DeepSeek V3.2 Exp, Q4_K_M (415.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (492.2 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 295.2 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run DeepSeek V3.2 Exp on a Mac?
Yes — Mac Studio (M3 Ultra, 512GB) and above can run DeepSeek V3.2 Exp. 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).
Can I run DeepSeek V3.2 Exp locally?
Yes — DeepSeek V3.2 Exp can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of DeepSeek V3.2 Exp?
At Q4_K_M, the download is about 411.24 GB. The full-precision BF16 version is 1370.79 GB. The smallest option (Q2_K) is 291.29 GB.
Which GPUs can run DeepSeek V3.2 Exp?
No single consumer GPU has enough VRAM to run DeepSeek V3.2 Exp at Q4_K_M (415.1 GB). Multi-GPU or professional hardware is required.
Which devices can run DeepSeek V3.2 Exp?
1 device with unified memory can run DeepSeek V3.2 Exp 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.