Back to leaderboard

qwen2.5-vl:7b

OLLAMA GGUF

qwen2vl · 7.6B · Q4_K_M

Excellent

Nov 8, 2026 · AMD Ryzen 7 8845HS

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 8bit

Good

Mar 3, 2026 · Apple M4

Global Score
84 vs 70
Hardware Fit
100 vs 93
Quality Score
77 vs 60

Hardware

qwen2.5-vl:7b qwen3.5-2b-mlx
MachineLENOVO 83DHMacBook Air
CPUAMD Ryzen 7 8845HSApple M4
Cores1610
RAM15 GB32 GB
GPUNVIDIA GeForce RTX 4060 Laptop GPU, AMD Radeon 780M GraphicsApple M4
OSMicrosoft Windows 11 Home Single Language 10.0.26300macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

qwen2.5-vl:7b qwen3.5-2b-mlx
Tokens/sec29.932.9
First chunk89 ms3096 ms
TTFT89 ms3.1 s
Load time10.9 sN/A
Memory usage4.8 GB2.5 GB
Memory %31%8%

HW Fit Score Breakdown

qwen2.5-vl:7b

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

qwen3.5-2b-mlx

Speed
50/50
TTFT
13/20
Memory
30/30

Quality

qwen2.5-vl:7b

Reasoning
16/20
Coding
14/20
Instruction
13/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3.5-2b-mlx

Reasoning
11/20
Coding
9/20
Instruction
14/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View qwen2.5-vl:7b details | View qwen3.5-2b-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