vicuna:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 1, 2026 · Apple M4
dolphin3:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
59 vs 74
Hardware Fit
97 vs 92
Quality Score
43 vs 66
Hardware
vicuna:7b dolphin3:8b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
vicuna:7b dolphin3:8b
Tokens/sec23.421.0
First chunkN/A314 ms
TTFT242 ms314 ms
Load time0.4 s0.8 s
Memory usage5.8 GB10.4 GB
Memory %18%33%
HW Fit Score Breakdown
vicuna:7b
Speed
37/50
TTFT
30/20
Memory
30/30
dolphin3:8b
Speed
42/50
TTFT
20/20
Memory
30/30
Quality
vicuna:7b
Reasoning
8/20
Coding
4/20
Instruction
10/20
Structured
12/15
Math
2/15
Multilingual
7/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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
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