Back to leaderboard

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

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

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

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

Hardware

qwen2.5:1.5b qwen3.5-9b-mlx
MachineShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRBMac mini
CPUZHAOXIN KaiXian KX-7000 KaiXian KX-7000Apple M4 Pro
Cores814
RAM30 GB64 GB
GPUZX C-1190Apple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26100macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

qwen2.5:1.5b qwen3.5-9b-mlx
Tokens/sec16.820.3
First chunk941 ms4216 ms
TTFT941 ms4.2 s
Load time0.2 sN/A
Memory usage1.0 GB5.6 GB
Memory %3%9%

HW Fit Score Breakdown

qwen2.5:1.5b

Speed
37/50
TTFT
20/20
Memory
30/30

qwen3.5-9b-mlx

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

Quality

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

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
View qwen2.5:1.5b details | View qwen3.5-9b-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