Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

tinyllama

OLLAMA GGUF
Marginal

Mar 6, 2026 · Apple M4

Global Score
77 vs 43
Hardware Fit
67 vs 100
Quality Score
81 vs 19

Hardware

qwen3.5-9b-mlx tinyllama
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-9b-mlx tinyllama
Tokens/sec20.3133.4
First chunk4216 ms61 ms
TTFT4.2 s61 ms
Load timeN/A0.5 s
Memory usage5.6 GB0.2 GB
Memory %9%1%

HW Fit Score Breakdown

qwen3.5-9b-mlx

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

tinyllama

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

tinyllama

Reasoning
2/20
Coding
2/20
Instruction
7/20
Structured
5/15
Math
0/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
View qwen3.5-9b-mlx details | View tinyllama 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