mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

qwen/qwen3-vl-30b

LM-STUDIO GGUF

qwen3vlmoe · 30B · Q4_K_M

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

Global Score

69 vs 92

Hardware Fit

50 vs 95

Quality Score

77 vs 90

Hardware

mistralai/devstral… qwen/qwen3-vl-30b

MachineMacBook AirASUS

CPUApple M4AMD Ryzen 5 5500

Cores1012

RAM32 GB31 GB

GPUApple M4Navi 44 [Radeon RX 9060 XT]

OSmacOS 26.3Nobara Linux 43

Archarm64x64

Power Modebalancedperformance

Performance

mistralai/devstral… qwen/qwen3-vl-30b

Tokens/sec5.724.8

First chunk5007 ms11 ms

TTFT5.0 s735 ms

Load timeN/A11.7 s

Memory usage13.2 GB0.6 GB

Memory %41%2%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

11/50

TTFT

9/20

Memory

30/30

qwen/qwen3-vl-30b

Speed

45/50

TTFT

20/20

Memory

30/30

Quality

mistralai/devstral-smal…

Reasoning

16/20

Coding

18/20

Instruction

13/20

Structured

14/15

Math

6/15

Multilingual

10/10

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

qwen/qwen3-vl-30b

Reasoning

19/20

Coding

19/20

Instruction

15/20

Structured

15/15

Math

12/15

Multilingual

10/10

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

View mistralai/devstral… details | View qwen/qwen3-vl-30b 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