Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

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
53 vs 65
Hardware Fit
72 vs 87
Quality Score
45 vs 56

Hardware

qwen3.5:9b qwen2.5:1.5b
MachineMacBook ProShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB
CPUApple M1 MaxZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Cores108
RAM32 GB30 GB
GPUApple M1 MaxZX C-1190
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26100
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5:9b qwen2.5:1.5b
Tokens/sec18.616.8
First chunk403 ms941 ms
TTFT10.2 s941 ms
Load time4.3 s0.2 s
Memory usage9.1 GB1.0 GB
Memory %28%3%

HW Fit Score Breakdown

qwen3.5:9b

Speed
38/50
TTFT
4/20
Memory
30/30

qwen2.5:1.5b

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

Quality

qwen3.5:9b

Reasoning
12/20
Coding
3/20
Instruction
5/20
Structured
6/15
Math
11/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak 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

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