Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

gemma4:e4b-mlx

OLLAMA GGUF
Excellent

Jul 7, 2026 · Apple M2 Pro

Global Score
59 vs 85
Hardware Fit
65 vs 95
Quality Score
57 vs 81

Hardware

qwen3.5-9b-mlx gemma4:e4b-mlx
MachineMac miniMacBook Pro
CPUApple M4Apple M2 Pro
Cores1010
RAM24 GB16 GB
GPUApple M4Apple M2 Pro
OSmacOS 26.3macOS 26.5
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-9b-mlx gemma4:e4b-mlx
Tokens/sec14.347.3
First chunk24 ms258 ms
TTFT13.4 s258 ms
Load time13.3 s5.1 s
Memory usage2.5 GB7.9 GB
Memory %10%49%

HW Fit Score Breakdown

qwen3.5-9b-mlx

Speed
32/50
TTFT
3/20
Memory
30/30

gemma4:e4b-mlx

Speed
50/50
TTFT
20/20
Memory
25/30

Quality

qwen3.5-9b-mlx

Reasoning
10/20
Coding
17/20
Instruction
5/20
Structured
9/15
Math
11/15
Multilingual
5/10
Reasoning: Weak Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Adequate Multilingual: Adequate

gemma4:e4b-mlx

Reasoning
15/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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