mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

GPT-OSS-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Aug 18, 2026 · Intel Core™ i7-14700F

Global Score

73 vs 93

Hardware Fit

64 vs 92

Quality Score

77 vs 93

Hardware

mistralai/devstral… GPT-OSS-20B:20b

MachineMacBook ProHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC

CPUApple M1 ProIntel Core™ i7-14700F

Cores1028

RAM32 GB128 GB

GPUApple M1 ProNVIDIA GeForce RTX 5080

OSmacOS 15.6.1Microsoft Windows 11 Enterprise 10.0.26200

Archarm64x64

Power Modebalancedbalanced

Performance

mistralai/devstral… GPT-OSS-20B:20b

Tokens/sec11.9178.6

First chunk7 ms695 ms

TTFT1.1 s1.4 s

Load timeN/A31.2 s

Memory usage19.7 GB11.9 GB

Memory %62%9%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

GPT-OSS-20B:20b

Speed

50/50

TTFT

12/20

Memory

30/30

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

GPT-OSS-20B:20b

Reasoning

19/20

Coding

18/20

Instruction

16/20

Structured

15/15

Math

15/15

Multilingual

10/10

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

View mistralai/devstral… details | View GPT-OSS-20B:20b 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