mistralai/devstral-small-2-2512
LM-STUDIO MLXmistral3 · 24B · 4bit
Mar 4, 2026 · Apple M4
qwen3.5-2b-mlx
LM-STUDIO MLXqwen3_5 · 2B · 8bit
Mar 3, 2026 · Apple M4
Global Score
69 vs 70
Hardware Fit
50 vs 93
Quality Score
77 vs 60
Hardware
mistralai/devstral… qwen3.5-2b-mlx
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
mistralai/devstral… qwen3.5-2b-mlx
Tokens/sec5.732.9
First chunk5007 ms3096 ms
TTFT5.0 s3.1 s
Load timeN/AN/A
Memory usage13.2 GB2.5 GB
Memory %41%8%
HW Fit Score Breakdown
mistralai/devstral-smal…
Speed
11/50
TTFT
9/20
Memory
30/30
qwen3.5-2b-mlx
Speed
50/50
TTFT
13/20
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
qwen3.5-2b-mlx
Reasoning
11/20
Coding
9/20
Instruction
14/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest