Back to leaderboard

qwen3.5-9b

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Excellent

Mar 3, 2026 · Apple M4

openai/gpt-oss-20b

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Excellent

Mar 4, 2026 · Apple M4

Global Score
81 vs 94
Hardware Fit
84 vs 100
Quality Score
79 vs 92

Hardware

qwen3.5-9b openai/gpt-oss-20b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-9b openai/gpt-oss-20b
Tokens/sec20.440.7
First chunk3034 ms824 ms
TTFT3.0 s1.3 s
Load timeN/AN/A
Memory usage5.6 GB11.3 GB
Memory %17%35%

HW Fit Score Breakdown

qwen3.5-9b

Speed
41/50
TTFT
14/20
Memory
29/30

openai/gpt-oss-20b

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

Quality

qwen3.5-9b

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

openai/gpt-oss-20b

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