mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 19, 2026 · Intel Core™ i7-14700F

Global Score

73 vs 85

Hardware Fit

64 vs 83

Quality Score

77 vs 86

Hardware

mistralai/devstral… Kimi-48B:48B

MachineMacBook ProHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC

CPUApple M1 ProIntel Core™ i7-14700F

Cores1028

RAM32 GB64 GB

GPUApple M1 ProNVIDIA GeForce RTX 5080

OSmacOS 15.6.1Microsoft Windows 11 Enterprise 10.0.26200

Archarm64x64

Power Modebalancedbalanced

Performance

mistralai/devstral… Kimi-48B:48B

Tokens/sec11.932.8

First chunk7 ms724 ms

TTFT1.1 s724 ms

Load timeN/A20.9 s

Memory usage19.7 GB25.8 GB

Memory %62%41%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

Kimi-48B:48B

Speed

36/50

TTFT

20/20

Memory

27/30

Quality

mistralai/devstral-smal…

Reasoning

17/20

Coding

16/20

Instruction

13/20

Structured

14/15

Math

7/15

Multilingual

10/10

Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

Kimi-48B:48B

Reasoning

16/20

Coding

17/20

Instruction

15/20

Structured

15/15

Math

13/15

Multilingual

10/10

Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

View mistralai/devstral… details | View Kimi-48B:48B details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest