Back to leaderboard

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Mar 10, 2026 · Apple M4

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Not Rec.

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
83 vs 20
Hardware Fit
65 vs 37
Quality Score
90 vs 12

Hardware

gpt-oss:20b qwen3.5:27b
MachineMac miniAZW GTR Pro
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM24 GB125 GB
GPUApple M4AMD Radeon 8060S
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

gpt-oss:20b qwen3.5:27b
Tokens/sec17.110.6
First chunk705 ms358 ms
TTFT10.2 s13.7 s
Load time23.1 s10.8 s
Memory usage13.1 GB39.7 GB
Memory %55%32%

HW Fit Score Breakdown

gpt-oss:20b

Speed
37/50
TTFT
5/20
Memory
23/30

qwen3.5:27b

Speed
9/50
TTFT
0/20
Memory
28/30

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

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

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest