gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
starling-lm:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 6, 2026 · Apple M4
Global Score
93 vs 65
Hardware Fit
85 vs 96
Quality Score
96 vs 52
Hardware
gpt-oss:20b starling-lm:7b
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB32 GB
GPUAMD Radeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
gpt-oss:20b starling-lm:7b
Tokens/sec47.123.8
First chunk320 ms232 ms
TTFT1.8 s232 ms
Load time3.8 s0.4 s
Memory usage16.4 GB5.3 GB
Memory %13%17%
HW Fit Score Breakdown
gpt-oss:20b
Speed
44/50
TTFT
11/20
Memory
30/30
starling-lm:7b
Speed
46/50
TTFT
20/20
Memory
30/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
starling-lm:7b
Reasoning
10/20
Coding
13/20
Instruction
8/20
Structured
3/15
Math
9/15
Multilingual
9/10
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