Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16

OLLAMA GGUF

qwen35 · 1.94B · BF16

Good

Aug 26, 2026 · Apple M1 Pro

Global Score
77 vs 66
Hardware Fit
67 vs 100
Quality Score
81 vs 52

Hardware

qwen3.5-9b-mlx hf.co/empero-ai/Qw…
MachineMac miniMacBook Pro
CPUApple M4 ProApple M1 Pro
Cores1410
RAM64 GB16 GB
GPUApple M4 ProApple M1 Pro
OSmacOS 15.7.4macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-9b-mlx hf.co/empero-ai/Qw…
Tokens/sec20.340.2
First chunk4216 ms101 ms
TTFT4.2 s101 ms
Load timeN/A2.6 s
Memory usage5.6 GB4.7 GB
Memory %9%30%

HW Fit Score Breakdown

qwen3.5-9b-mlx

Speed
29/50
TTFT
8/20
Memory
30/30

hf.co/empero-ai/Qwen3.8…

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

Quality

qwen3.5-9b-mlx

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

hf.co/empero-ai/Qwen3.8…

Reasoning
15/20
Coding
9/20
Instruction
8/20
Structured
1/15
Math
15/15
Multilingual
4/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

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