qwen3.5:4b-mlx
OLLAMA GGUFnvfp4
Aug 24, 2026 · Apple M2
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
Global Score
53 vs 93
Hardware Fit
81 vs 85
Quality Score
41 vs 96
Hardware
qwen3.5:4b-mlx gpt-oss:20b
MachineMac miniAZW GTR Pro
CPUApple M2AMD RYZEN AI MAX+ 395
Cores832
RAM8 GB125 GB
GPUApple M2AMD Radeon 8060S
OSmacOS 26.5.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
qwen3.5:4b-mlx gpt-oss:20b
Tokens/sec24.847.1
First chunk317 ms320 ms
TTFT7.4 s1.8 s
Load time0.0 s3.8 s
Memory usage3.9 GB16.4 GB
Memory %49%13%
HW Fit Score Breakdown
qwen3.5:4b-mlx
Speed
50/50
TTFT
6/20
Memory
25/30
gpt-oss:20b
Speed
44/50
TTFT
11/20
Memory
30/30
Quality
qwen3.5:4b-mlx
Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong
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
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