Back to leaderboard

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Jul 3, 2026 · AMD RYZEN AI MAX+ 395

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Not Rec.

Apr 1, 2026 · Apple M4

Global Score
94 vs 4
Hardware Fit
91 vs 13
Quality Score
95 vs 0

Hardware

gpt-oss:20b qwen3.5:27b
MachineFramework Desktop (AMD Ryzen AI Max 300 Series)Mac mini
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM64 GB24 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M4
OSMicrosoft Windows 11 Pro for Workstations 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

gpt-oss:20b qwen3.5:27b
Tokens/sec48.03.5
First chunk357 ms1781 ms
TTFT2.3 s52.0 s
Load time0.2 s13.4 s
Memory usage16.4 GB21.3 GB
Memory %26%89%

HW Fit Score Breakdown

gpt-oss:20b

Speed
50/50
TTFT
11/20
Memory
30/30

qwen3.5:27b

Speed
7/50
TTFT
0/20
Memory
6/30

Quality

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

qwen3.5:27b

Reasoning
0/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
View gpt-oss:20b details | View qwen3.5:27b details

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