Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Jun 17, 2026 · ZHAOXIN KaiXian KX-7000 KaiXian KX-7000

Global Score
77 vs 65
Hardware Fit
67 vs 87
Quality Score
81 vs 56

Hardware

qwen3.5-9b-mlx qwen2.5:1.5b
MachineMac miniShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB
CPUApple M4 ProZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Cores148
RAM64 GB30 GB
GPUApple M4 ProZX C-1190
OSmacOS 15.7.4Microsoft Windows 11 Pro 10.0.26100
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5-9b-mlx qwen2.5:1.5b
Tokens/sec20.316.8
First chunk4216 ms941 ms
TTFT4.2 s941 ms
Load timeN/A0.2 s
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

qwen2.5:1.5b

Speed
37/50
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

qwen2.5:1.5b

Reasoning
8/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5-9b-mlx details | View qwen2.5:1.5b 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