mistralai/devstral-small-2-2512
LM-STUDIO MLXmistral3 · 24B · 4bit
Oct 20, 2026 · Apple M1 Pro
qwen3.8-27b-mlx
LM-STUDIO UNKNOWN27B
Aug 17, 2026 · Apple M5 Max
Global Score
73 vs 66
Hardware Fit
64 vs 91
Quality Score
77 vs 55
Hardware
mistralai/devstral… qwen3.8-27b-mlx
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M5 Max
Cores1018
RAM32 GB64 GB
GPUApple M1 ProApple M5 Max
OSmacOS 15.6.1macOS 27.0
Archarm64arm64
Power Modebalancedbalanced
Performance
mistralai/devstral… qwen3.8-27b-mlx
Tokens/sec11.933.2
First chunk7 ms7 ms
TTFT1.1 s311 ms
Load timeN/AN/A
Memory usage19.7 GB0.5 GB
Memory %62%1%
HW Fit Score Breakdown
mistralai/devstral-smal…
Speed
25/50
TTFT
20/20
Memory
19/30
qwen3.8-27b-mlx
Speed
41/50
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
qwen3.8-27b-mlx
Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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