vicuna:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 1, 2026 · Apple M4
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
59 vs 79
Hardware Fit
97 vs 59
Quality Score
43 vs 88
Hardware
vicuna:7b GPT-20B:20b
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
vicuna:7b GPT-20B:20b
Tokens/sec23.419.3
First chunkN/A2004 ms
TTFT242 ms10.4 s
Load time0.4 s10.4 s
Memory usage5.8 GB12.9 GB
Memory %18%20%
HW Fit Score Breakdown
vicuna:7b
Speed
37/50
TTFT
30/20
Memory
30/30
GPT-20B:20b
Speed
26/50
TTFT
3/20
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
GPT-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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