gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 10, 2026 · Apple M4
gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
Global Score
83 vs 81
Hardware Fit
65 vs 100
Quality Score
90 vs 73
Hardware
gpt-oss:20b gemma3n:latest
MachineMac miniSupermicro AS -2015HS-TNR
CPUApple M4AMD EPYC 9654P 96-Core Processor
Cores1064
RAM24 GB128 GB
GPUApple M4GH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSmacOS 26.3Ubuntu 24.04.3 LTS
Archarm64x64
Power Modebalancedperformance
Performance
gpt-oss:20b gemma3n:latest
Tokens/sec17.1108.7
First chunk705 ms333 ms
TTFT10.2 s333 ms
Load time23.1 s4.5 s
Memory usage13.1 GB8.6 GB
Memory %55%7%
HW Fit Score Breakdown
gpt-oss:20b
Speed
37/50
TTFT
5/20
Memory
23/30
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
gemma3n:latest
Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
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