Mistral Large 4 1T A52B vs Kimi K2.7 Code

Mistral Large 4 1T A52B and Kimi K2.7 Code match in llmrun Score, with values of 118.0 versus 118.1; neither fits 24 GB.

Run Kimi K2.7 Code in the cloud →

Model A · Mistral AI

Mistral Large 4 1T A52B

118.0llmrun Score

1000B · 52B active · 1M context · Other · Sep 2026

VisionFunctions

Model B · Moonshot AI

Kimi K2.7 Code

118.1llmrun Score

1026.9B · 33.3B active · 256K context · Other · Jun 2026

VisionCodeFunctions

Which should you choose?

Choose Mistral Large 4 1T A52B if you want…

Ahead on the benchmarks
12 of 15 shared boards
Longer context window
1M vs 256K tokens
Newer release
Sep 2026 vs Jun 2026

Choose Kimi K2.7 Code if you want…

Also does code
Mistral Large 4 1T A52B doesn't list it

On your hardware

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

MemoryMistral Large 4 1T A52BKimi K2.7 Code

8 GB

RTX 4060 · 8 GB tier

Mistral Large 4 1T A52B

Doesn't fit

smallest quant needs 304.3 GB

Kimi K2.7 Code

Doesn't fit

smallest quant needs 283.8 GB

12 GB

RTX 3060 12GB · 12 GB tier

Mistral Large 4 1T A52B

Doesn't fit

smallest quant needs 304.3 GB

Kimi K2.7 Code

Doesn't fit

smallest quant needs 283.8 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Mistral Large 4 1T A52B

Doesn't fit

smallest quant needs 304.3 GB

Kimi K2.7 Code

Doesn't fit

smallest quant needs 283.8 GB

24 GBreference

RTX 4090 · 24 GB tier

Mistral Large 4 1T A52B

Doesn't fit

smallest quant needs 304.3 GB

Kimi K2.7 Code

Doesn't fit

smallest quant needs 283.8 GB

32 GB

RTX 5090 · 32 GB tier

Mistral Large 4 1T A52B

Doesn't fit

smallest quant needs 304.3 GB

Kimi K2.7 Code

Doesn't fit

smallest quant needs 283.8 GB

48 GB

RTX A6000 · 48 GB tier

Mistral Large 4 1T A52B

Doesn't fit

smallest quant needs 304.3 GB

Kimi K2.7 Code

Doesn't fit

smallest quant needs 283.8 GB

Mac 32 GB

Mac Mini M4 · Macs

Mistral Large 4 1T A52B

Doesn't fit

smallest quant needs 304.3 GB

Kimi K2.7 Code

Doesn't fit

smallest quant needs 283.8 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Mistral Large 4 1T A52B

Doesn't fit

smallest quant needs 304.3 GB

Kimi K2.7 Code

Doesn't fit

smallest quant needs 283.8 GB

Mac 128 GB

Mac Studio M4 Max · Macs

Mistral Large 4 1T A52B

Doesn't fit

smallest quant needs 304.3 GB

Kimi K2.7 Code

Doesn't fit

smallest quant needs 283.8 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

Mistral Large 4 1T A52B Kimi K2.7 Code

Overall

Mistral Large 4 1T A52B

118.0115–121

Kimi K2.7 Code

118.1115–121

Coding

Mistral Large 4 1T A52B

112.3108–117

Kimi K2.7 Code

114.8110–120

Agents

Mistral Large 4 1T A52B

116.6109–125

Kimi K2.7 Code

118.7112–125

Math

Mistral Large 4 1T A52B

121.7118–125

Kimi K2.7 Code

120.7116–125

Science

Mistral Large 4 1T A52B

120.4109–132

Kimi K2.7 Code

117.6107–129

Reasoning

Mistral Large 4 1T A52B

120.3114–127

Kimi K2.7 Code

115.3106–125

Mistral Large 4 1T A52B · #18 of 104 open models · #16 of 101 that fit ≤640 GB

Kimi K2.7 Code · #17 of 104 open models · #15 of 101 that fit ≤640 GB

Benchmarks

15 shared boards: Mistral Large 4 1T A52B leads 12, Kimi K2.7 Code leads 2 · Benchmarks imported Oct 2026

BoardMistral Large 4 1T A52BKimi K2.7 Code

GPQA Diamond

Mistral Large 4 1T A52B

88.1%#16/100 open

IndependentEpoch AI · Oct 2026

Kimi K2.7 Code

87.9%#17/100 open

IndependentEpoch AI · Jun 2026

LiveBench Coding

Mistral Large 4 1T A52B

77.2#8/20 open

IndependentLiveBench · Jun 2026

Kimi K2.7 Code

74.0#12/20 open

IndependentLiveBench · Jun 2026

LiveBench Reasoning

Mistral Large 4 1T A52B

83.9#9/20 open

IndependentLiveBench · Jun 2026

Kimi K2.7 Code

82.8#10/20 open

IndependentLiveBench · Jun 2026

AIME 2024/2025

Mistral Large 4 1T A52B

98.3%#4/88 open

IndependentEpoch AI · Oct 2026

Kimi K2.7 Code

95.6%#9/88 open

IndependentEpoch AI · Jun 2026

FrontierMath

Mistral Large 4 1T A52B

58.6%#8/19 open

IndependentEpoch AI · Oct 2026

Kimi K2.7 Code

54.0%#12/19 open

IndependentEpoch AI · Jun 2026

LiveBench Math

Mistral Large 4 1T A52B

93.6#2/20 open

IndependentLiveBench · Jun 2026

Kimi K2.7 Code

79.6#19/20 open

IndependentLiveBench · Jun 2026

SciCode

Mistral Large 4 1T A52B

54.2%#7/70 open

Lab-reportedEpoch AI · Oct 2026

Kimi K2.7 Code

47.8%#20/70 open

Lab-reportedEpoch AI · Jun 2026

SimpleQA

Mistral Large 4 1T A52B

20.0%#17/19 open

IndependentEpoch AI · Oct 2026

Kimi K2.7 Code

36.5%#10/19 open

IndependentEpoch AI · Jun 2026

FrontierMath Tier 4

Mistral Large 4 1T A52B

26.8%#8/15 open

IndependentEpoch AI · Oct 2026

Kimi K2.7 Code

12.2%#13/15 open

IndependentEpoch AI · Jun 2026

FrontierCode

Mistral Large 4 1T A52B

39.4%#4/13 open

Lab-reportedEpoch AI · Oct 2026

Kimi K2.7 Code

30.1%#6/13 open

Lab-reportedEpoch AI · Jun 2026

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

ALE-Bench

Mistral Large 4 1T A52B

1213.2#8/46 open

Lab-reportedEpoch AI · Oct 2026

Kimi K2.7 Code

886.2#19/46 open

Lab-reportedEpoch AI · Jun 2026

APEX-Agents

Mistral Large 4 1T A52B

51.6%#5/20 open

Lab-reportedEpoch AI · Oct 2026

Kimi K2.7 Code

37.6%#14/20 open

Lab-reportedEpoch AI · Jun 2026

Chess Puzzles

Mistral Large 4 1T A52B

33.0%#6/16 open

IndependentEpoch AI · Oct 2026

Kimi K2.7 Code

14.0%#15/16 open

IndependentEpoch AI · Jun 2026

CritPt

Mistral Large 4 1T A52B

10.6%#14/82 open

Lab-reportedEpoch AI · Oct 2026

Kimi K2.7 Code

10.0%#15/82 open

Lab-reportedEpoch AI · Jun 2026

Surface Evolver Bench

Mistral Large 4 1T A52B

28.1%#11/14 open

Lab-reportedEpoch AI · Oct 2026

Kimi K2.7 Code

48.8%#5/14 open

Lab-reportedEpoch AI · Jun 2026

Only Mistral Large 4 1T A52B (13)

Only Kimi K2.7 Code (6)

VRAM by quantization

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

QuantMistral Large 4 1T A52BKimi K2.7 Code

Q2_K

Mistral Large 4 1T A52B

429 GB380.7 GB file

32K 483 GB · 128K 657 GB

Kimi K2.7 Code

440 GB~436.4 GB file

32K 439 GB · 128K 446 GB

Q3_K_M

Mistral Large 4 1T A52B

491 GB~487.5 GB file

32K 546 GB · 128K 720 GB

Kimi K2.7 Code

504 GB463.6 GB file

32K 503 GB · 128K 510 GB

Q4_K_M

Mistral Large 4 1T A52B

604 GB634.8 GB file

32K 658 GB · 128K 832 GB

Kimi K2.7 Code

620 GB~616.1 GB file

32K 619 GB · 128K 626 GB

Q5_K_M

Mistral Large 4 1T A52B

716 GB~712.5 GB file

32K 771 GB · 128K 945 GB

Kimi K2.7 Code

736 GB~731.6 GB file

32K 734 GB · 128K 741 GB

Q6_K

Mistral Large 4 1T A52B

829 GB~825.0 GB file

32K 883 GB · 128K 1057 GB

Kimi K2.7 Code

851 GB~847.2 GB file

32K 850 GB · 128K 857 GB

Q8_0

Mistral Large 4 1T A52B

1004 GB~1000.0 GB file

32K 1058 GB · 128K 1232 GB

Kimi K2.7 Code

1031 GB~1026.9 GB file

32K 1029 GB · 128K 1036 GB

8 more quants

IQ2_XXS

Mistral Large 4 1T A52B

279 GB302.5 GB file

32K 333 GB · 128K 507 GB

Kimi K2.7 Code

286 GB317.8 GB file

32K 285 GB · 128K 292 GB

IQ2_S

Mistral Large 4 1T A52B

not listed

Kimi K2.7 Code

325 GB334.8 GB file

32K 324 GB · 128K 330 GB

IQ2_M

Mistral Large 4 1T A52B

not listed

Kimi K2.7 Code

350 GB318.0 GB file

32K 349 GB · 128K 356 GB

IQ3_XXS

Mistral Large 4 1T A52B

391 GB423.5 GB file

32K 446 GB · 128K 620 GB

Kimi K2.7 Code

402 GB376.9 GB file

32K 401 GB · 128K 407 GB

IQ3_S

Mistral Large 4 1T A52B

not listed

Kimi K2.7 Code

440 GB418.8 GB file

32K 439 GB · 128K 446 GB

Q3_K_L

Mistral Large 4 1T A52B

not listed

Kimi K2.7 Code

530 GB493.9 GB file

32K 529 GB · 128K 536 GB

IQ4_XS

Mistral Large 4 1T A52B

not listed

Kimi K2.7 Code

556 GB495.1 GB file

32K 555 GB · 128K 561 GB

BF16

Mistral Large 4 1T A52B

2004 GB~2000.0 GB file

32K 2058 GB · 128K 2232 GB

Kimi K2.7 Code

2058 GB~2053.8 GB file

32K 2056 GB · 128K 2063 GB

How to run each

Mistral Large 4 1T A52B

Ollama · Q4_K_M

$ollama run hf.co/ggml-org/Mistral-Large-4-1T-A52B-GGUF:Q4_K_M

All ways to run Mistral Large 4 1T A52B →

Kimi K2.7 Code

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Kimi-K2.7-Code-GGUF

All ways to run Kimi K2.7 Code →

Specifications

Specifications of Mistral Large 4 1T A52B and Kimi K2.7 Code
Spec	Mistral Large 4 1T A52B	Kimi K2.7 Code
Publisher	Mistral AI	Moonshot AI
Parameters	1000B	1026.9B
Active parameters	52B per token	33B per token
Architecture	MistralLarge4ForConditionalGeneration	KimiK25ForConditionalGeneration
Context	1M tokens	256K tokens
Modalities	Vision, Function-calling	Vision, Code, Function-calling
License	Other	Other
Released	Sep 2026	Jun 2026

Frequently Asked Questions

Which is better, Mistral Large 4 1T A52B or Kimi K2.7 Code?

Mistral Large 4 1T A52B and Kimi K2.7 Code match in llmrun Score, with values of 118.0 versus 118.1; neither fits 24 GB. Choose Mistral Large 4 1T A52B for ahead on the benchmarks and longer context window; choose Kimi K2.7 Code for also does code.

Which needs less VRAM, Mistral Large 4 1T A52B or Kimi K2.7 Code?

At Q4_K_M, Mistral Large 4 1T A52B requires 603.9 GB while Kimi K2.7 Code needs 620.0 GB, making Mistral Large 4 1T A52B the easier model to run on your local setup.

Can I run Mistral Large 4 1T A52B or Kimi K2.7 Code on a 16 GB GPU?

Mistral Large 4 1T A52B does not fit (smallest quant needs 304.3 GB); Kimi K2.7 Code does not fit (smallest quant needs 283.8 GB).

Which has a longer context window, Mistral Large 4 1T A52B or Kimi K2.7 Code?

Mistral Large 4 1T A52B supports 1,048,576 tokens and Kimi K2.7 Code supports 262,144 tokens.