Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Apr 1, 2026 · Apple M4

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

Global Score
82 vs 59
Hardware Fit
85 vs 63
Quality Score
81 vs 58

Hardware

openai/gpt-oss-20b qwen3.8-27b-mlx
MachineMac miniMacBook Pro
CPUApple M4Apple M5 Max
Cores1018
RAM24 GB64 GB
GPUApple M4Apple M5 Max
OSmacOS 26.3macOS 27.0
Archarm64arm64
Power Modebalancedbalanced

Performance

openai/gpt-oss-20b qwen3.8-27b-mlx
Tokens/sec31.818.3
First chunk32 ms4 ms
TTFT8.4 s530 ms
Load time22.7 sN/A
Memory usage0.0 GB38.5 GB
Memory %0%60%

HW Fit Score Breakdown

openai/gpt-oss-20b

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

qwen3.8-27b-mlx

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

Quality

openai/gpt-oss-20b

Reasoning
19/20
Coding
14/20
Instruction
9/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.8-27b-mlx

Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

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