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-vl:4b-instruct

OLLAMA GGUF

qwen3vl · 4.4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

Global Score
65 vs 83
Hardware Fit
87 vs 96
Quality Score
56 vs 78

Hardware

qwen2.5:1.5b qwen3-vl:4b-instruct
MachineShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRBMac Studio
CPUZHAOXIN KaiXian KX-7000 KaiXian KX-7000Apple M2 Max
Cores812
RAM30 GB96 GB
GPUZX C-1190Apple M2 Max
OSMicrosoft Windows 11 Pro 10.0.26100macOS 26.1
Archx64arm64
Power Modebalancedbalanced

Performance

qwen2.5:1.5b qwen3-vl:4b-instruct
Tokens/sec16.891.2
First chunk941 ms150 ms
TTFT941 ms150 ms
Load time0.2 s5.3 s
Memory usage1.0 GB42.5 GB
Memory %3%44%

HW Fit Score Breakdown

qwen2.5:1.5b

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

qwen3-vl:4b-instruct

Speed
50/50
TTFT
20/20
Memory
26/30

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-vl:4b-instruct

Reasoning
14/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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