Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

qwen3.5-0.8b-mlx

LM-STUDIO MLX

qwen3_5 · 0.8B · 8bit

Good

Mar 3, 2026 · Apple M4

Global Score
77 vs 60
Hardware Fit
67 vs 96
Quality Score
81 vs 44

Hardware

qwen3.5-9b-mlx qwen3.5-0.8b-mlx
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 qwen3.5-0.8b-mlx
Tokens/sec20.3108.0
First chunk4216 ms2568 ms
TTFT4.2 s2.6 s
Load timeN/AN/A
Memory usage5.6 GB1.0 GB
Memory %9%3%

HW Fit Score Breakdown

qwen3.5-9b-mlx

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

qwen3.5-0.8b-mlx

Speed
50/50
TTFT
16/20
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

qwen3.5-0.8b-mlx

Reasoning
10/20
Coding
3/20
Instruction
11/20
Structured
12/15
Math
3/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

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