Back to leaderboard

qwen2.5:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Excellent

Nov 3, 2026 · Intel Gen Intel® Core™ i9-12900HX

qwen3-vl:4b-instruct

OLLAMA GGUF

qwen3vl · 4.4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

Global Score
85 vs 83
Hardware Fit
100 vs 96
Quality Score
79 vs 78

Hardware

qwen2.5:7b qwen3-vl:4b-instruct
MachineMACHENIKE L16PMac Studio
CPUIntel Gen Intel® Core™ i9-12900HXApple M2 Max
Cores2412
RAM32 GB96 GB
GPUNVIDIA GeForce RTX 4060 Laptop GPUApple M2 Max
OSMicrosoft Windows 11 专业版 10.0.26300macOS 26.1
Archx64arm64
Power Modebalancedbalanced

Performance

qwen2.5:7b qwen3-vl:4b-instruct
Tokens/sec52.491.2
First chunk48 ms150 ms
TTFT48 ms150 ms
Load time2.0 s5.3 s
Memory usage4.4 GB42.5 GB
Memory %14%44%

HW Fit Score Breakdown

qwen2.5:7b

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

qwen3-vl:4b-instruct

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

Quality

qwen2.5:7b

Reasoning
14/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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
View qwen2.5:7b details | View qwen3-vl:4b-instruct 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