dolphin3:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Mar 6, 2026 · Apple M4
mistralai/magistral-small-2509
LM-STUDIO MLXmistral3 · 24B · 4bit
Mar 4, 2026 · Apple M4
Global Score
74 vs 74
Hardware Fit
92 vs 66
Quality Score
66 vs 78
Hardware
dolphin3:8b mistralai/magistra…
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
dolphin3:8b mistralai/magistra…
Tokens/sec21.07.9
First chunk314 ms1356 ms
TTFT314 ms1.4 s
Load time0.8 sN/A
Memory usage10.4 GB13.2 GB
Memory %33%41%
HW Fit Score Breakdown
dolphin3:8b
Speed
42/50
TTFT
20/20
Memory
30/30
mistralai/magistral-sma…
Speed
16/50
TTFT
20/20
Memory
30/30
Quality
dolphin3:8b
Reasoning
12/20
Coding
13/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
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
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