Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Not Rec.

Mar 19, 2026 · Apple M4

qwen3.5-0.8b-mlx

LM-STUDIO MLX

qwen3_5 · 0.8B · 8bit

Good

Mar 3, 2026 · Apple M4

Global Score
77 vs 60
Hardware Fit
67 vs 96
Quality Score
81 vs 44

Hardware

openai/gpt-oss-20b qwen3.5-0.8b-mlx
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM24 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

openai/gpt-oss-20b qwen3.5-0.8b-mlx
Tokens/sec30.5108.0
First chunk18 ms2568 ms
TTFT30.0 s2.6 s
Load timeN/AN/A
Memory usage15.8 GB1.0 GB
Memory %66%3%

HW Fit Score Breakdown

openai/gpt-oss-20b

Speed
50/50
TTFT
0/20
Memory
17/30

qwen3.5-0.8b-mlx

Speed
50/50
TTFT
16/20
Memory
30/30

Quality

openai/gpt-oss-20b

Reasoning
19/20
Coding
11/20
Instruction
12/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5-0.8b-mlx

Reasoning
10/20
Coding
3/20
Instruction
11/20
Structured
12/15
Math
3/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

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