mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score

73 vs 67

Hardware Fit

64 vs 77

Quality Score

77 vs 63

Hardware

mistralai/devstral… llama3.2:3b

MachineMacBook ProLENOVO 20U30029MB

CPUApple M1 ProIntel Core™ i5-10210U

Cores108

RAM32 GB15 GB

GPUApple M1 ProCometLake-U GT2 [UHD Graphics]

OSmacOS 15.6.1Pop 24.04 LTS

Archarm64x64

Power Modebalancedlow-power

Performance

mistralai/devstral… llama3.2:3b

Tokens/sec11.910.0

First chunk7 ms1166 ms

TTFT1.1 s1.2 s

Load timeN/A6.8 s

Memory usage19.7 GB3.8 GB

Memory %62%25%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

llama3.2:3b

Speed

27/50

TTFT

20/20

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

llama3.2:3b

Reasoning

11/20

Coding

15/20

Instruction

13/20

Structured

12/15

Math

3/15

Multilingual

9/10

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

View mistralai/devstral… details | View llama3.2:3b 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