DeepSeek V4 Pro 0813 — Hardware Requirements & GPU Compatibility
Chat
DeepSeek-V4-Pro-0813 is DeepSeek's official release of DeepSeek-V4-Pro, superseding an earlier preview build with stronger agentic capabilities aimed at production use. It is a large Mixture-of-Experts model at roughly 1.65 trillion total parameters, built on the V4-Pro architecture with a DSpark speculative-decoding module attached, and it supports configurable reasoning effort (low, high, or max) to control how much it deliberates before answering. It ships with a roughly 1 million token context window and is released under the MIT license, so it can be used and modified freely. At this scale, running it locally means multi-GPU server hardware with hundreds of gigabytes of memory even at 4-bit; most users will access it through a hosted endpoint instead.
DeepSeek V4 Pro 0813 runs on a multi-GPU server
Q4_K_M needs ~990.8 GB · about 8× H200 SXM 141 GB
Score 129.2#6 of 100 open#6 of 99 that fit ≤1 TBMIT
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
llmrun Composite Score →
129.2
- 90% range 127.4–131.0
- #6 of 100 open models
- #6 of 99 that fit ≤1 TB
Run DeepSeek V4 Pro 0813
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve deepseek-ai/DeepSeek-V4-Pro-0813 --max-model-len 16384 --tensor-parallel-size 8Size the nodes from the table above
Download: DeepSeek-V4-Pro-0813-Q4_K_M.gguf990.30 GBunsloth
Other ways
each opens step-by-stepRun in cloud
Rent 8× H200 SXM node · Q4_K_M
- Estimated hourly price
- ~$28.72/hr
- est., whole server
- GPUs
- 8 GPUs
- 1.1 TB of VRAM
How Much VRAM Does DeepSeek V4 Pro 0813 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 639.9 GB | 640.3 GB | 3-bit · i-quant — Importance-weighted 3-bit | Runs on 6× H200 SXM 141 GB | |
| 701.8 GB | 702.2 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Runs on 6× H200 SXM 141 GB | |
| 805.0 GB | 805.4 GB | 3-bit medium — 3-bit medium quantization | Runs on 7× H200 SXM 141 GB | |
| 825.6 GB | 826 GB | 4-bit · legacy — 4-bit legacy quantization | Runs on 7× H200 SXM 141 GB | |
| 928.7 GB | 929.2 GB | 4-bit · legacy+ — 4-bit legacy quantization with offset | Runs on 8× H200 SXM 141 GB | |
| 990.6 GB | 991.1 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Runs on 8× H200 SXM 141 GB | |
| 1176.3 GB | 1176.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Runs on 7× B200 192 GB | |
| 1362.0 GB | 1362.4 GB | 6-bit, very good — 6-bit quantization, very good quality | Runs on 8× B200 192 GB | |
| 1650.8 GB | 1651.3 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Runs on 3 nodes of 8× H100 SXM | |
| 3301.3 GB | 3301.7 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on 6 nodes of 8× H100 SXM |
Selected Q4_K_M
4-bit medium quantization990.8GBat 16K context
- Weights
- 990.3 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Server-class: ~990.8 GB at 16K context · about 8× H200 SXM 141 GB
Which Hardware Can Run DeepSeek V4 Pro 0813?
Q4_K_M · 990.6 GBDeepSeek V4 Pro 0813 (Q4_K_M) requires 990.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1288+ GB is recommended. Using the full 1049K context window can add up to 14.3 GB, bringing total usage to 1004.9 GB. No consumer GPU has enough memory.
Needs server-class hardware
DeepSeek V4 Pro 0813 runs on a multi-GPU server · Q4_K_M needs ~990.8 GB
| Hardware | Quant | Memory | Context | Hardware page | |
|---|---|---|---|---|---|
| 8× H200 SXM 141 GB · 1.1 TB | Q4_K_M | 990.8 GB | 1M ctx | H200 SXM → | Q4_K_M · 990.8 GB · 1M ctx |
| 6× B200 192 GB · 1.2 TB | Q4_K_M | 990.8 GB | 1M ctx | B200 → | Q4_K_M · 990.8 GB · 1M ctx |
By VRAM tier · typical GPUs and Macs at Q4_K_M
Consumer GPUs (up to 32 GB) and Macs up to 512 GB: too small for this model (needs ≥ 640.1 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
How good is DeepSeek V4 Pro 0813?
The llmrun Score merges 21 public benchmark boards into a single figure, where 100 represents the average for open models.
Score vs VRAM in the ≤1 TB tier
- DeepSeek V4 Pro 0813
- Other models
- Best Score for its VRAM
#6 of 99 that fit ≤1 TB
Each dot is a model at the best quant that fits ≤1 TB. The line joins the models with the best Score for their VRAM; a dot below it is beaten by a model that needs no more memory.
Full ≤1 TB ranking →Benchmarks
The 6 boards that weigh most in the llmrun Score, of 23 with a result for this model; badges show who ran the test.
- GPQA Diamond
Epoch AI · Aug 2026Independent
Independent91.7%
#3/98 open
- LMArena Text
LMArena · Oct 2026Arena
Arena1464.6
#9/187 open
- LiveBench Coding
LiveBench · Jun 2026Independent
Independent77.2
#7/19 open
- LiveBench Reasoning
LiveBench · Jun 2026Independent
Independent85.8
#6/19 open
- AIME 2024/2025
Epoch AI · Aug 2026Independent
Independent98.6%
#1/86 open
- FrontierMath
Epoch AI · Aug 2026Independent
Independent64.6%
#5/17 open
In the ≤1 TB class
99 models fit ≤1 TBSame Score, only models that fit ≤1 TB at their best quant: this model's peers by memory need.
- #1
MiMo V2.6 Pro RLXiaomi
133.4
614.1 GB
- #2
Kimi K3Moonshot AI
132.8
766.5 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
129.5
458.4 GB
Alternatives to DeepSeek V4 Pro 0813
DeepSeek V4 family · 12 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.
Runner-up at this size
DeepSeek V4 Pro
DeepSeek
- 12.7 lower Score
- 31 GB less VRAM
Score 116.5 · 959.8 GB
Fits in less VRAM
GLM 5.3
Z.ai
- 0.9 higher Score
- 537.1 GB less VRAM
Score 130.1 · 453.8 GB
Other vendor
MiMo V2.6 Pro RL
Xiaomi
- 4.2 higher Score
- 376.8 GB less VRAM
Score 133.4 · 614.1 GB
Similar models
10| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Kimi K3Moonshot AI | 132.8 | 1670 GB | —needs > 24 GB | similar score |
| MiMo V2.6 Flash RLXiaomi | 131.9 | 186.5 GB | —needs > 24 GB | similar score |
| Muse Spark Open 816B A42BMeta | 125.3 | 551.9 GB | —needs > 24 GB | similar score |
| Qwen3.8 27BAlibaba | 122.1 | 17.9 GB | ~38 | similar score |
| Kimi K2.6Moonshot AI | 120.9 | 617.6 GB | —needs > 24 GB | similar score |
| MiMo V2.5 ProXiaomi | 116.4 | 616 GB | —needs > 24 GB | similar score |
| InklingThinking Machines | 116.0 | 575.1 GB | —needs > 24 GB | similar score |
| LongCat 2.0Meituan | — | 3917.9 GB | —needs > 24 GB | same size |
| Nex N2.5 Maxnex-agi | — | 3202.1 GB | —needs > 24 GB | same size |
| DeepSeek V4.1 FlashDeepSeek | 129.5 | 458.4 GB | —needs > 24 GB | same family |
Specifications
- Publisher
- DeepSeek
- Family
- DeepSeek V4
- Parameters
- 1650.5B
- Active parameters
- 102B per token
- Architecture
- DeepseekV4ForCausalLM
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 129,280
- Release Date
- 2026-08-13
- License
- MIT
Frequently Asked Questions
How much VRAM does DeepSeek V4 Pro 0813 need?
DeepSeek V4 Pro 0813 requires 990.6 GB of VRAM at Q4_K_M, or 3301.3 GB at BF16. Full 1049K context adds up to 14.3 GB (1004.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1650.5B × 4.8 bits ÷ 8 = 990.3 GB
KV Cache + Overhead ≈ 0.3 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 ≈ 14.6 GB (at full 1049K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run DeepSeek V4 Pro 0813?
No — DeepSeek V4 Pro 0813 requires at least 639.9 GB at IQ3_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
What's the best quantization for DeepSeek V4 Pro 0813?
For DeepSeek V4 Pro 0813, Q4_K_M (990.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (1176.3 GB) provides better quality if you have the VRAM. The smallest option is IQ3_XXS at 639.9 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run DeepSeek V4 Pro 0813 on a Mac?
DeepSeek V4 Pro 0813 requires at least 639.9 GB at IQ3_XXS. None of the 146 Macs we list has that much usable memory (the largest has 508.5 GB after macOS overhead).
Can I run DeepSeek V4 Pro 0813 locally?
Yes — DeepSeek V4 Pro 0813 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of DeepSeek V4 Pro 0813?
At Q4_K_M, the download is about 990.30 GB. The full-precision BF16 version is 3301.00 GB. The smallest option (IQ3_XXS) is 639.57 GB.
Which GPUs can run DeepSeek V4 Pro 0813?
No single consumer GPU has enough VRAM to run DeepSeek V4 Pro 0813 at Q4_K_M (990.6 GB). Multi-GPU or professional hardware is required.
Which devices can run DeepSeek V4 Pro 0813?
DeepSeek V4 Pro 0813 requires at least 990.6 GB at Q4_K_M, which exceeds the usable memory of every unified-memory device we list (the largest has 508.5 GB).