gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Apr 1, 2026 · Apple M4
gemma4:e4b-it-q8_0
OLLAMA GGUFgemma4 · 8.0B · Q8_0
Aug 25, 2026 · Apple M1 Pro
Global Score
87 vs 88
Hardware Fit
83 vs 100
Quality Score
88 vs 83
Hardware
gpt-oss:20b gemma4:e4b-it-q8_0
MachineMac miniMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM24 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
gpt-oss:20b gemma4:e4b-it-q8_0
Tokens/sec24.327.8
First chunk529 ms204 ms
TTFT4.5 s204 ms
Load time11.2 s6.6 s
Memory usage13.1 GB5.0 GB
Memory %55%31%
HW Fit Score Breakdown
gpt-oss:20b
Speed
49/50
TTFT
11/20
Memory
23/30
gemma4:e4b-it-q8_0
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
11/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:e4b-it-q8_0
Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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