qwen3.5:27b
OLLAMA GGUFqwen35 · 27.8B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
May 25, 2026 · Apple M4 Pro
Global Score
20 vs 94
Hardware Fit
37 vs 92
Quality Score
12 vs 95
Hardware
qwen3.5:27b gpt-oss:20b
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M4 Pro
Cores3214
RAM125 GB48 GB
GPUAMD Radeon 8060SApple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 26.4.1
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3.5:27b gpt-oss:20b
Tokens/sec10.654.5
First chunk358 ms318 ms
TTFT13.7 s2.9 s
Load time10.8 s4.0 s
Memory usage39.7 GB16.4 GB
Memory %32%34%
HW Fit Score Breakdown
qwen3.5:27b
Speed
9/50
TTFT
0/20
Memory
28/30
gpt-oss:20b
Speed
50/50
TTFT
13/20
Memory
29/30
Quality
qwen3.5:27b
Reasoning
2/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
0/15
Multilingual
8/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Strong
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
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