Back to leaderboard

hf.co/bartowski/ai9stars_G9v3-3B-GGUF:BF16

OLLAMA GGUF

llama · 2.99B · BF16

Good

Aug 26, 2026 · Apple M1 Pro

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
64 vs 62
Hardware Fit
92 vs 35
Quality Score
52 vs 73

Hardware

hf.co/bartowski/ai… qwen3.5-4b-mlx
MachineMacBook ProMac mini
CPUApple M1 ProApple M4 Pro
Cores1014
RAM16 GB64 GB
GPUApple M1 ProApple M4 Pro
OSmacOS 26.6.2macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

hf.co/bartowski/ai… qwen3.5-4b-mlx
Tokens/sec29.90.0
First chunk108 ms5548 ms
TTFT108 ms5.5 s
Load time3.4 sN/A
Memory usage8.9 GB2.9 GB
Memory %56%5%

HW Fit Score Breakdown

hf.co/bartowski/ai9star…

Speed
50/50
TTFT
20/20
Memory
22/30

qwen3.5-4b-mlx

Speed
0/50
TTFT
6/20
Memory
29/30

Quality

hf.co/bartowski/ai9star…

Reasoning
17/20
Coding
14/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor

qwen3.5-4b-mlx

Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong
View hf.co/bartowski/ai… details | View qwen3.5-4b-mlx details

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