mistralai/magistral-small-2509
LM-STUDIO MLXmistral3 · 24B · 4bit
Mar 4, 2026 · Apple M4
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
74 vs 86
Hardware Fit
66 vs 78
Quality Score
78 vs 89
Hardware
mistralai/magistra… Kimi-48B:48B
MachineMacBook AirGMKtec NucBox EVO-T2S
CPUApple M4Intel Core™ Ultra X7 358H
Cores1016
RAM32 GB64 GB
GPUApple M4Intel(R) Arc(TM) B390 GPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
mistralai/magistra… Kimi-48B:48B
Tokens/sec7.922.8
First chunk1356 ms721 ms
TTFT1.4 s721 ms
Load timeN/A23.0 s
Memory usage13.2 GB25.5 GB
Memory %41%40%
HW Fit Score Breakdown
mistralai/magistral-sma…
Speed
16/50
TTFT
20/20
Memory
30/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
mistralai/magistral-sma…
Reasoning
14/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
Kimi-48B:48B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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