Back to leaderboard

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

qwen3-coder-30b-a3b-instruct-mlx

LM-STUDIO MLX

qwen3_moe · 30B · 4bit

Excellent

Oct 20, 2026 · Apple M1 Pro

Global Score
73 vs 87
Hardware Fit
64 vs 85
Quality Score
77 vs 88

Hardware

mistralai/devstral… qwen3-coder-30b-a3…
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M1 Pro
Cores1010
RAM32 GB32 GB
GPUApple M1 ProApple M1 Pro
OSmacOS 15.6.1macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced

Performance

mistralai/devstral… qwen3-coder-30b-a3…
Tokens/sec11.945.7
First chunk7 ms17 ms
TTFT1.1 s390 ms
Load timeN/AN/A
Memory usage19.7 GB22.4 GB
Memory %62%70%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed
25/50
TTFT
20/20
Memory
19/30

qwen3-coder-30b-a3b-ins…

Speed
50/50
TTFT
20/20
Memory
15/30

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

qwen3-coder-30b-a3b-ins…

Reasoning
15/20
Coding
19/20
Instruction
17/20
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 qwen3-coder-30b-a3… 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