DeepSeek V4 Pro vs DeepSeek V4 Pro 0813

DeepSeek V4 Pro 0813 leads llmrun Score 129.2 to 116.5; neither fits 24 GB.

Model A · DeepSeek

DeepSeek V4 Pro

116.5llmrun Score

1598.8B · 50.7B active · 1M context · MIT · Apr 2026

Chat

Model B · DeepSeek

DeepSeek V4 Pro 0813

129.2llmrun Score

1650.5B · 102.3B active · 1M context · MIT · Aug 2026

Chat

Which should you choose?

Choose DeepSeek V4 Pro 0813 if you want…

Higher llmrun Score
129.2 vs 116.5
Stronger at coding
125.2 vs 110.6
Stronger at reasoning
131.1 vs 117.0
Ahead on the benchmarks
18 of 18 shared boards
Newer release
Aug 2026 vs Apr 2026

DeepSeek V4 Pro: no clear edge over DeepSeek V4 Pro 0813 in the data we have.

On your hardware

Each model at its default quant (Q4_K_M), a smaller one when it must. Estimates, ±20%.

MemoryDeepSeek V4 ProDeepSeek V4 Pro 0813

8 GB

RTX 4060 · 8 GB tier

DeepSeek V4 Pro

Doesn't fit

smallest quant needs 680 GB

DeepSeek V4 Pro 0813

Doesn't fit

smallest quant needs 640.1 GB

12 GB

RTX 3060 12GB · 12 GB tier

DeepSeek V4 Pro

Doesn't fit

smallest quant needs 680 GB

DeepSeek V4 Pro 0813

Doesn't fit

smallest quant needs 640.1 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

DeepSeek V4 Pro

Doesn't fit

smallest quant needs 680 GB

DeepSeek V4 Pro 0813

Doesn't fit

smallest quant needs 640.1 GB

24 GBreference

RTX 4090 · 24 GB tier

DeepSeek V4 Pro

Doesn't fit

smallest quant needs 680 GB

DeepSeek V4 Pro 0813

Doesn't fit

smallest quant needs 640.1 GB

32 GB

RTX 5090 · 32 GB tier

DeepSeek V4 Pro

Doesn't fit

smallest quant needs 680 GB

DeepSeek V4 Pro 0813

Doesn't fit

smallest quant needs 640.1 GB

48 GB

RTX A6000 · 48 GB tier

DeepSeek V4 Pro

Doesn't fit

smallest quant needs 680 GB

DeepSeek V4 Pro 0813

Doesn't fit

smallest quant needs 640.1 GB

Mac 32 GB

Mac Mini M4 · Macs

DeepSeek V4 Pro

Doesn't fit

smallest quant needs 680 GB

DeepSeek V4 Pro 0813

Doesn't fit

smallest quant needs 640.1 GB

Mac 64 GB

Mac Studio M4 Max · Macs

DeepSeek V4 Pro

Doesn't fit

smallest quant needs 680 GB

DeepSeek V4 Pro 0813

Doesn't fit

smallest quant needs 640.1 GB

Mac 128 GB

Mac Studio M4 Max · Macs

DeepSeek V4 Pro

Doesn't fit

smallest quant needs 680 GB

DeepSeek V4 Pro 0813

Doesn't fit

smallest quant needs 640.1 GB

Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).

llmrun Score

with its 90% range · bars share one scale

DeepSeek V4 Pro DeepSeek V4 Pro 0813

Overall

DeepSeek V4 Pro

116.5114–119

DeepSeek V4 Pro 0813

129.2127–131

Coding

DeepSeek V4 Pro

110.6105–116

DeepSeek V4 Pro 0813

125.2119–132

Math

DeepSeek V4 Pro

117.6114–122

DeepSeek V4 Pro 0813

128.3126–131

Science

DeepSeek V4 Pro

122.3111–134

DeepSeek V4 Pro 0813

126.3114–138

Reasoning

DeepSeek V4 Pro

117.0110–124

DeepSeek V4 Pro 0813

131.1128–134

DeepSeek V4 Pro · #16 of 100 open models · #16 of 99 that fit ≤1 TB

DeepSeek V4 Pro 0813 · #6 of 100 open models · #6 of 99 that fit ≤1 TB

Benchmarks

18 shared boards: DeepSeek V4 Pro leads 0, DeepSeek V4 Pro 0813 leads 18 · Benchmarks imported Oct 2026

BoardDeepSeek V4 ProDeepSeek V4 Pro 0813

GPQA Diamond

DeepSeek V4 Pro

90.9%#5/98 open

IndependentEpoch AI · Apr 2026

DeepSeek V4 Pro 0813

91.7%#3/98 open

IndependentEpoch AI · Aug 2026

LiveBench Coding

DeepSeek V4 Pro

70.0#16/19 open

IndependentLiveBench · Jun 2026

DeepSeek V4 Pro 0813

77.2#7/19 open

IndependentLiveBench · Jun 2026

LiveBench Reasoning

DeepSeek V4 Pro

82.7#10/19 open

IndependentLiveBench · Jun 2026

DeepSeek V4 Pro 0813

85.8#6/19 open

IndependentLiveBench · Jun 2026

AIME 2024/2025

DeepSeek V4 Pro

96.7%#5/86 open

IndependentEpoch AI · Apr 2026

DeepSeek V4 Pro 0813

98.6%#1/86 open

IndependentEpoch AI · Aug 2026

FrontierMath

DeepSeek V4 Pro

45.3%#12/17 open

IndependentEpoch AI · Apr 2026

DeepSeek V4 Pro 0813

64.6%#5/17 open

IndependentEpoch AI · Aug 2026

LiveBench Math

DeepSeek V4 Pro

90.7#3/19 open

IndependentLiveBench · Jun 2026

DeepSeek V4 Pro 0813

95.1#1/19 open

IndependentLiveBench · Jun 2026

SciCode

DeepSeek V4 Pro

50.0%#12/66 open

Lab-reportedEpoch AI · Apr 2026

DeepSeek V4 Pro 0813

51.0%#9/66 open

Lab-reportedEpoch AI · Aug 2026

SimpleQA

DeepSeek V4 Pro

47.0%#4/17 open

IndependentEpoch AI · Apr 2026

DeepSeek V4 Pro 0813

52.9%#2/17 open

IndependentEpoch AI · Aug 2026

FrontierMath Tier 4

DeepSeek V4 Pro

2.4%#13/13 open

IndependentEpoch AI · Apr 2026

DeepSeek V4 Pro 0813

26.8%#6/13 open

IndependentEpoch AI · Aug 2026

WeirdML

DeepSeek V4 Pro

48.9%#10/46 open

IndependentEpoch AI · Apr 2026

DeepSeek V4 Pro 0813

66.2%#4/46 open

IndependentEpoch AI · Aug 2026

17 more boards (other shared and single-model boards)

FrontierCode

DeepSeek V4 Pro

17.6%#9/12 open

Lab-reportedEpoch AI · Apr 2026

DeepSeek V4 Pro 0813

28.5%#6/12 open

Lab-reportedEpoch AI · Aug 2026

ALE-Bench

DeepSeek V4 Pro

1006.1#10/43 open

Lab-reportedEpoch AI · Apr 2026

DeepSeek V4 Pro 0813

1403.2#2/43 open

Lab-reportedEpoch AI · Aug 2026

Chess Puzzles

DeepSeek V4 Pro

19.0%#12/14 open

IndependentEpoch AI · Apr 2026

DeepSeek V4 Pro 0813

46.0%#2/14 open

IndependentEpoch AI · Aug 2026

CritPt

DeepSeek V4 Pro

12.9%#9/66 open

Lab-reportedEpoch AI · Apr 2026

DeepSeek V4 Pro 0813

18.0%#5/66 open

Lab-reportedEpoch AI · Aug 2026

DTBench

DeepSeek V4 Pro

90.7%#6/68 open

Lab-reportedEpoch AI · Apr 2026

DeepSeek V4 Pro 0813

93.9%#1/68 open

Lab-reportedEpoch AI · Aug 2026

LMCA

DeepSeek V4 Pro

41.2%#8/54 open

Lab-reportedEpoch AI · Apr 2026

DeepSeek V4 Pro 0813

45.5%#5/54 open

Lab-reportedEpoch AI · Aug 2026

Mystery Game Puzzles

DeepSeek V4 Pro

17.0%#11/18 open

IndependentEpoch AI · Apr 2026

DeepSeek V4 Pro 0813

43.0%#2/18 open

IndependentEpoch AI · Aug 2026

ProofBench

DeepSeek V4 Pro

16.0%#14/26 open

Lab-reportedEpoch AI · Apr 2026

DeepSeek V4 Pro 0813

50.0%#7/26 open

Lab-reportedEpoch AI · Aug 2026

LMArena Text

DeepSeek V4 Pro

1457.8#11/187 open

ArenaLMArena · Oct 2026

DeepSeek V4 Pro 0813

1464.6#9/187 open

ArenaLMArena · Oct 2026

LMArena WebDev

DeepSeek V4 Pro

1464.2#20/52 open

ArenaLMArena · Oct 2026

DeepSeek V4 Pro 0813

1582.0#11/52 open

ArenaLMArena · Oct 2026

Only DeepSeek V4 Pro (4)

Only DeepSeek V4 Pro 0813 (3)

VRAM by quantization

Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.

QuantDeepSeek V4 ProDeepSeek V4 Pro 0813

Q2_K

DeepSeek V4 Pro

680 GB574.1 GB file

32K 680 GB · 128K 682 GB

DeepSeek V4 Pro 0813

702 GB587.3 GB file

32K 702 GB · 128K 704 GB

Q3_K_M

DeepSeek V4 Pro

780 GB748.7 GB file

32K 780 GB · 128K 782 GB

DeepSeek V4 Pro 0813

805 GB763.7 GB file

32K 805 GB · 128K 807 GB

Q4_0

DeepSeek V4 Pro

not listed

DeepSeek V4 Pro 0813

826 GB885.3 GB file

32K 826 GB · 128K 827 GB

Q4_K_M

DeepSeek V4 Pro

960 GB954.6 GB file

32K 960 GB · 128K 961 GB

DeepSeek V4 Pro 0813

991 GB~990.3 GB file

32K 991 GB · 128K 992 GB

Q5_K_M

DeepSeek V4 Pro

1140 GB~1139.2 GB file

32K 1140 GB · 128K 1141 GB

DeepSeek V4 Pro 0813

1176 GB~1176.0 GB file

32K 1177 GB · 128K 1178 GB

Q6_K

DeepSeek V4 Pro

1319 GB~1319.0 GB file

32K 1320 GB · 128K 1321 GB

DeepSeek V4 Pro 0813

1362 GB~1361.7 GB file

32K 1362 GB · 128K 1364 GB

Q8_0

DeepSeek V4 Pro

1599 GB1671.8 GB file

32K 1600 GB · 128K 1601 GB

DeepSeek V4 Pro 0813

1651 GB~1650.5 GB file

32K 1651 GB · 128K 1653 GB

3 more quants

IQ3_XXS

DeepSeek V4 Pro

not listed

DeepSeek V4 Pro 0813

640 GB619.5 GB file

32K 640 GB · 128K 642 GB

Q4_1

DeepSeek V4 Pro

not listed

DeepSeek V4 Pro 0813

929 GB983.6 GB file

32K 929 GB · 128K 930 GB

BF16

DeepSeek V4 Pro

3198 GB~3197.7 GB file

32K 3198 GB · 128K 3200 GB

DeepSeek V4 Pro 0813

3301 GB~3301.0 GB file

32K 3302 GB · 128K 3303 GB

How to run each

DeepSeek V4 Pro

Ollama · Q4_K_M

$ollama run hf.co/teamblobfish/DeepSeek-V4-Pro-GGUF:Q4_K_M

All ways to run DeepSeek V4 Pro →

DeepSeek V4 Pro 0813

Ollama · Q4_K_M

$ollama run hf.co/unsloth/DeepSeek-V4-Pro-0813-GGUF

All ways to run DeepSeek V4 Pro 0813 →

Specifications

Specifications of DeepSeek V4 Pro and DeepSeek V4 Pro 0813
Spec	DeepSeek V4 Pro	DeepSeek V4 Pro 0813
Publisher	DeepSeek	DeepSeek
Parameters	1598.8B	1650.5B
Active parameters	51B per token	102B per token
Architecture	DeepseekV4ForCausalLM	DeepseekV4ForCausalLM
Context	1M tokens	1M tokens
Modalities	Chat	Chat
License	MIT	MIT
Released	Apr 2026	Aug 2026

Frequently Asked Questions

Which is better, DeepSeek V4 Pro or DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813 leads llmrun Score 129.2 to 116.5; neither fits 24 GB. Choose DeepSeek V4 Pro 0813 for higher llmrun Score and stronger at coding.

Which needs less VRAM, DeepSeek V4 Pro or DeepSeek V4 Pro 0813?

At Q4_K_M, DeepSeek V4 Pro requires 959.6 GB while DeepSeek V4 Pro 0813 needs 990.6 GB, making DeepSeek V4 Pro the easier model to run on your local setup.

Can I run DeepSeek V4 Pro or DeepSeek V4 Pro 0813 on a 16 GB GPU?

DeepSeek V4 Pro does not fit (smallest quant needs 680 GB); DeepSeek V4 Pro 0813 does not fit (smallest quant needs 640.1 GB).

Which has a longer context window, DeepSeek V4 Pro or DeepSeek V4 Pro 0813?

DeepSeek V4 Pro supports 1,048,576 tokens and DeepSeek V4 Pro 0813 supports 1,048,576 tokens.