DeepSeek V4 Pro 0813 vs Kimi K3.1 Pro
Kimi K3.1 Pro leads llmrun Score 142.8 to 129.2; neither fits 24 GB.
Run Kimi K3.1 Pro in the cloud →
Model A · DeepSeek
DeepSeek V4 Pro 08131650.5B · 102.3B active · 1M context · MIT · Aug 2026
Model B · Moonshot AI
Kimi K3.1 Pro2780.1B · 106B active · 1M context · Other · Nov 2026
Choose DeepSeek V4 Pro 0813 if you want…
Lighter on memory
990.6 vs 1673.8 GB at Q4_K_M
More permissive license
MIT vs Other
Choose Kimi K3.1 Pro if you want…
Higher llmrun Score
142.8 vs 129.2
Stronger at coding
140.7 vs 125.2
Stronger at science
138.0 vs 126.1
Ahead on the benchmarks
4 of 4 shared boards
Also does vision
DeepSeek V4 Pro 0813 doesn't list it
On your hardware
Each model at its default quant (Q4_K_M), a smaller one when it must. Estimates, ±20%.
8 GB
RTX 4060 · 8 GB tier
DeepSeek V4 Pro 0813
Doesn't fit
smallest quant needs 640.1 GB
Kimi K3.1 Pro
Doesn't fit
smallest quant needs 1225.5 GB
12 GB
RTX 3060 12GB · 12 GB tier
DeepSeek V4 Pro 0813
Doesn't fit
smallest quant needs 640.1 GB
Kimi K3.1 Pro
Doesn't fit
smallest quant needs 1225.5 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
DeepSeek V4 Pro 0813
Doesn't fit
smallest quant needs 640.1 GB
Kimi K3.1 Pro
Doesn't fit
smallest quant needs 1225.5 GB
24 GBreference
RTX 4090 · 24 GB tier
DeepSeek V4 Pro 0813
Doesn't fit
smallest quant needs 640.1 GB
Kimi K3.1 Pro
Doesn't fit
smallest quant needs 1225.5 GB
32 GB
RTX 5090 · 32 GB tier
DeepSeek V4 Pro 0813
Doesn't fit
smallest quant needs 640.1 GB
Kimi K3.1 Pro
Doesn't fit
smallest quant needs 1225.5 GB
48 GB
RTX A6000 · 48 GB tier
DeepSeek V4 Pro 0813
Doesn't fit
smallest quant needs 640.1 GB
Kimi K3.1 Pro
Doesn't fit
smallest quant needs 1225.5 GB
Mac 32 GB
Mac Mini M4 · Macs
DeepSeek V4 Pro 0813
Doesn't fit
smallest quant needs 640.1 GB
Kimi K3.1 Pro
Doesn't fit
smallest quant needs 1225.5 GB
Mac 64 GB
Mac Studio M4 Max · Macs
DeepSeek V4 Pro 0813
Doesn't fit
smallest quant needs 640.1 GB
Kimi K3.1 Pro
Doesn't fit
smallest quant needs 1225.5 GB
Mac 128 GB
Mac Studio M4 Max · Macs
DeepSeek V4 Pro 0813
Doesn't fit
smallest quant needs 640.1 GB
Kimi K3.1 Pro
Doesn't fit
smallest quant needs 1225.5 GB
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
DeepSeek V4 Pro 0813
Kimi K3.1 Pro
Coding
DeepSeek V4 Pro 0813
Kimi K3.1 Pro
Math
DeepSeek V4 Pro 0813
Kimi K3.1 Pro
no data
Science
DeepSeek V4 Pro 0813
Kimi K3.1 Pro
Reasoning
DeepSeek V4 Pro 0813
Kimi K3.1 Pro
no data
DeepSeek V4 Pro 0813 · #8 of 106 open models · #7 of 105 that fit ≤1 TB
Kimi K3.1 Pro · #1 of 106 open models · #1 of 106 that fit ≤2 TB
Benchmarks
4 shared boards: DeepSeek V4 Pro 0813 leads 0, Kimi K3.1 Pro leads 4 · Benchmarks imported Nov 2026
DeepSeek V4 Pro 0813
51.0%#14/72 open
Lab-reportedEpoch AI · Aug 2026
Kimi K3.1 Pro
60.8%#2/72 open
Lab-reportedEpoch AI · Oct 2026
DeepSeek V4 Pro 0813
1403.2#5/48 open
Lab-reportedEpoch AI · Aug 2026
Kimi K3.1 Pro
1932.8#1/48 open
Lab-reportedEpoch AI · Oct 2026
DeepSeek V4 Pro 0813
18.0%#8/84 open
Lab-reportedEpoch AI · Aug 2026
Kimi K3.1 Pro
24.6%#2/84 open
Lab-reportedEpoch AI · Oct 2026
DeepSeek V4 Pro 0813
50.0%#8/31 open
Lab-reportedEpoch AI · Aug 2026
Kimi K3.1 Pro
91.0%#1/31 open
Lab-reportedEpoch AI · Oct 2026
19 more boards (other shared and single-model boards)
Only DeepSeek V4 Pro 0813 (19)
- GPQA Diamond91.7%
- LMArena Text1465.1
- LiveBench Coding77.2
- LiveBench Reasoning85.8
- AIME 2024/202598.6%
- FrontierMath64.6%
- LMArena WebDev1581.9
- LiveBench Math95.1
- ARC-AGI-261.3%
- ARC-AGI90.5%
- SimpleQA52.9%
- FrontierMath Tier 426.8%
- WeirdML66.2%
- FrontierCode28.5%
- APEX-Agents47.3%
- Chess Puzzles46.0%
- DTBench93.9%
- LMCA45.5%
- Mystery Game Puzzles43.0%
VRAM by quantization
Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.
Q2_K
DeepSeek V4 Pro 0813
702 GB587.3 GB file
32K 702 GB · 128K 704 GB
Kimi K3.1 Pro
1187 GB~1181.5 GB file
32K 1269 GB · 128K 1531 GB
Q3_K_M
DeepSeek V4 Pro 0813
805 GB763.7 GB file
32K 805 GB · 128K 807 GB
Kimi K3.1 Pro
1361 GB~1355.3 GB file
32K 1443 GB · 128K 1705 GB
Q4_0
DeepSeek V4 Pro 0813
826 GB885.3 GB file
32K 826 GB · 128K 827 GB
Kimi K3.1 Pro
not listed
Q4_K_M
DeepSeek V4 Pro 0813
991 GB~990.3 GB file
32K 991 GB · 128K 992 GB
Kimi K3.1 Pro
1674 GB~1668.1 GB file
32K 1756 GB · 128K 2018 GB
Q5_K_M
DeepSeek V4 Pro 0813
1176 GB~1176.0 GB file
32K 1177 GB · 128K 1178 GB
Kimi K3.1 Pro
1987 GB~1980.8 GB file
32K 2069 GB · 128K 2331 GB
Q6_K
DeepSeek V4 Pro 0813
1362 GB~1361.7 GB file
32K 1362 GB · 128K 1364 GB
Kimi K3.1 Pro
2299 GB~2293.6 GB file
32K 2381 GB · 128K 2643 GB
Q8_0
DeepSeek V4 Pro 0813
1651 GB~1650.5 GB file
32K 1651 GB · 128K 1653 GB
Kimi K3.1 Pro
2786 GB~2780.1 GB file
32K 2868 GB · 128K 3130 GB
3 more quants
IQ3_XXS
DeepSeek V4 Pro 0813
640 GB619.5 GB file
32K 640 GB · 128K 642 GB
Kimi K3.1 Pro
not listed
Q4_1
DeepSeek V4 Pro 0813
929 GB983.6 GB file
32K 929 GB · 128K 930 GB
Kimi K3.1 Pro
not listed
BF16
DeepSeek V4 Pro 0813
3301 GB~3301.0 GB file
32K 3302 GB · 128K 3303 GB
Kimi K3.1 Pro
5566 GB~5560.2 GB file
32K 5648 GB · 128K 5910 GB
DeepSeek V4 Pro 0813
Ollama · Q4_K_M
ollama run hf.co/unsloth/DeepSeek-V4-Pro-0813-GGUFKimi K3.1 Pro
No local recipe · Q4_K_M
No GGUF repo entry exists for this model yet.
All ways to run Kimi K3.1 Pro →| Spec | DeepSeek V4 Pro 0813 | Kimi K3.1 Pro |
|---|---|---|
| Publisher | DeepSeek | Moonshot AI |
| Parameters | 1650.5B | 2780.1B |
| Active parameters | 102B per token | 106B per token |
| Architecture | DeepseekV4ForCausalLM | KimiK31ForConditionalGeneration |
| Context | 1M tokens | 1M tokens |
| Modalities | Chat | Vision, Chat |
| License | MIT | Other |
| Released | Aug 2026 | Nov 2026 |
Frequently Asked Questions
Which is better, DeepSeek V4 Pro 0813 or Kimi K3.1 Pro?
Kimi K3.1 Pro leads llmrun Score 142.8 to 129.2; neither fits 24 GB. Choose DeepSeek V4 Pro 0813 for lighter on memory and more permissive license; choose Kimi K3.1 Pro for higher llmrun Score and stronger at coding.
Which needs less VRAM, DeepSeek V4 Pro 0813 or Kimi K3.1 Pro?
At Q4_K_M, DeepSeek V4 Pro 0813 requires 990.6 GB while Kimi K3.1 Pro needs 1673.8 GB, making DeepSeek V4 Pro 0813 the easier model to run on your local setup.
Can I run DeepSeek V4 Pro 0813 or Kimi K3.1 Pro on a 16 GB GPU?
DeepSeek V4 Pro 0813 does not fit (smallest quant needs 640.1 GB); Kimi K3.1 Pro does not fit (smallest quant needs 1225.5 GB).
Which has a longer context window, DeepSeek V4 Pro 0813 or Kimi K3.1 Pro?
DeepSeek V4 Pro 0813 supports 1,048,576 tokens and Kimi K3.1 Pro supports 1,048,576 tokens.