phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
mistralai/devstral-small-2-2512
LM-STUDIO MLXmistral3 · 24B · 4bit
Mar 4, 2026 · Apple M4
Global Score
64 vs 69
Hardware Fit
100 vs 50
Quality Score
48 vs 77
Hardware
phi3:3.8b mistralai/devstral…
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
phi3:3.8b mistralai/devstral…
Tokens/sec42.05.7
First chunkN/A5007 ms
TTFT142 ms5.0 s
Load time1.1 sN/A
Memory usage16.0 GB13.2 GB
Memory %50%41%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
mistralai/devstral-smal…
Speed
11/50
TTFT
9/20
Memory
30/30
Quality
phi3:3.8b
Reasoning
12/20
Coding
3/20
Instruction
11/20
Structured
10/15
Math
5/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate
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
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