Back to leaderboard

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

May 25, 2026 · Apple M4 Pro

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Excellent

Aug 18, 2026 · Apple M4 Max

Global Score
94 vs 81
Hardware Fit
92 vs 68
Quality Score
95 vs 87

Hardware

gpt-oss:20b qwen/qwen3.8-27b
MachineMacBook ProMacBook Pro
CPUApple M4 ProApple M4 Max
Cores1416
RAM48 GB128 GB
GPUApple M4 ProApple M4 Max
OSmacOS 26.4.1macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced

Performance

gpt-oss:20b qwen/qwen3.8-27b
Tokens/sec54.516.4
First chunk318 ms5 ms
TTFT2.9 s742 ms
Load time4.0 sN/A
Memory usage16.4 GB38.5 GB
Memory %34%30%

HW Fit Score Breakdown

gpt-oss:20b

Speed
50/50
TTFT
13/20
Memory
29/30

qwen/qwen3.8-27b

Speed
18/50
TTFT
20/20
Memory
30/30

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

qwen/qwen3.8-27b

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View gpt-oss:20b details | View qwen/qwen3.8-27b 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