Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

gemma4:e4b-it-q8_0

OLLAMA GGUF

gemma4 · 8.0B · Q8_0

Excellent

Aug 25, 2026 · Apple M1 Pro

Global Score
58 vs 88
Hardware Fit
68 vs 100
Quality Score
54 vs 83

Hardware

qwen3.5-9b-mlx gemma4:e4b-it-q8_0
MachineMac miniMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM24 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-9b-mlx gemma4:e4b-it-q8_0
Tokens/sec16.727.8
First chunk23 ms204 ms
TTFT14.1 s204 ms
Load timeN/A6.6 s
Memory usage7.8 GB5.0 GB
Memory %33%31%

HW Fit Score Breakdown

qwen3.5-9b-mlx

Speed
36/50
TTFT
3/20
Memory
29/30

gemma4:e4b-it-q8_0

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

Quality

qwen3.5-9b-mlx

Reasoning
10/20
Coding
16/20
Instruction
4/20
Structured
9/15
Math
10/15
Multilingual
5/10
Reasoning: Adequate Coding: Strong Instruction Following: Poor Structured Output: Adequate Math: Adequate Multilingual: Adequate

gemma4:e4b-it-q8_0

Reasoning
14/20
Coding
19/20
Instruction
17/20
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