Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 18, 2026 · Apple M4 Max

openai/gpt-oss-20b

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
87 vs 83
Hardware Fit
83 vs 80
Quality Score
88 vs 84

Hardware

qwen/qwen3.8-27b openai/gpt-oss-20b
MachineMacBook ProMacBook Pro
CPUApple M4 MaxApple M5 Max
Cores1618
RAM128 GB64 GB
GPUApple M4 MaxApple M5 Max
OSmacOS 26.5.2macOS 27.0
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.8-27b openai/gpt-oss-20b
Tokens/sec29.1131.7
First chunk9 ms7 ms
TTFT650 ms30.0 s
Load timeN/AN/A
Memory usage21.0 GB15.8 GB
Memory %16%25%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
33/50
TTFT
20/20
Memory
30/30

openai/gpt-oss-20b

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

Quality

qwen/qwen3.8-27b

Reasoning
18/20
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

openai/gpt-oss-20b

Reasoning
18/20
Coding
13/20
Instruction
14/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong 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