Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor

Global Score
59 vs 81
Hardware Fit
65 vs 100
Quality Score
57 vs 73

Hardware

qwen3.5-9b-mlx gemma3n:latest
MachineMac miniSupermicro AS -2015HS-TNR
CPUApple M4AMD EPYC 9654P 96-Core Processor
Cores1064
RAM24 GB128 GB
GPUApple M4GH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSmacOS 26.3Ubuntu 24.04.3 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.5-9b-mlx gemma3n:latest
Tokens/sec14.3108.7
First chunk24 ms333 ms
TTFT13.4 s333 ms
Load time13.3 s4.5 s
Memory usage2.5 GB8.6 GB
Memory %10%7%

HW Fit Score Breakdown

qwen3.5-9b-mlx

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

gemma3n:latest

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

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

gemma3n:latest

Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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