mistralai/devstral-small-2-2512
LM-STUDIO MLXmistral3 · 24B · 4bit
Mar 4, 2026 · Apple M4
gemma4:e4b-it-q8_0
OLLAMA GGUFgemma4 · 8.0B · Q8_0
Aug 26, 2026 · Apple M1 Pro
Global Score
69 vs 91
Hardware Fit
50 vs 88
Quality Score
77 vs 92
Hardware
mistralai/devstral… gemma4:e4b-it-q8_0
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
mistralai/devstral… gemma4:e4b-it-q8_0
Tokens/sec5.730.0
First chunk5007 ms311 ms
TTFT5.0 s6.2 s
Load timeN/A6.9 s
Memory usage13.2 GB5.0 GB
Memory %41%31%
HW Fit Score Breakdown
mistralai/devstral-smal…
Speed
11/50
TTFT
9/20
Memory
30/30
gemma4:e4b-it-q8_0
Speed
50/50
TTFT
8/20
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
gemma4:e4b-it-q8_0
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
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