gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Apr 1, 2026 · Apple M4
starling-lm:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
87 vs 63
Hardware Fit
83 vs 97
Quality Score
88 vs 49
Hardware
gpt-oss:20b starling-lm:7b
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM24 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gpt-oss:20b starling-lm:7b
Tokens/sec24.323.7
First chunk529 msN/A
TTFT4.5 s234 ms
Load time11.2 s0.4 s
Memory usage13.1 GB5.3 GB
Memory %55%17%
HW Fit Score Breakdown
gpt-oss:20b
Speed
49/50
TTFT
11/20
Memory
23/30
starling-lm:7b
Speed
37/50
TTFT
30/20
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
starling-lm:7b
Reasoning
11/20
Coding
13/20
Instruction
6/20
Structured
3/15
Math
8/15
Multilingual
8/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Poor 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