Back to leaderboard

qwen2.5vl:3b

OLLAMA GGUF

qwen25vl · 3.8B · Q4_K_M

Good

Oct 31, 2026 · Intel Gen Intel® Core™ i9-12900H

mlx-community/meta-llama-3.1-8b-instruct

LM-STUDIO MLX

llama · 8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

Global Score
77 vs 77
Hardware Fit
100 vs 100
Quality Score
67 vs 67

Hardware

qwen2.5vl:3b mlx-community/meta…
MachineMicro-Star International Co., Ltd. Stealth GS77 12UHMac mini
CPUIntel Gen Intel® Core™ i9-12900HApple M4 Pro
Cores2014
RAM32 GB64 GB
GPUIntel(R) Iris(R) Xe Graphics, NVIDIA GeForce RTX 3080 Laptop GPUApple M4 Pro
OSMicrosoft Windows 11 Home 10.0.26200macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

qwen2.5vl:3b mlx-community/meta…
Tokens/sec106.554.3
First chunk68 ms277 ms
TTFT68 ms277 ms
Load time17.8 sN/A
Memory usage2.8 GB4.2 GB
Memory %9%7%

HW Fit Score Breakdown

qwen2.5vl:3b

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

mlx-community/meta-llam…

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

Quality

qwen2.5vl:3b

Reasoning
11/20
Coding
15/20
Instruction
12/20
Structured
14/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

mlx-community/meta-llam…

Reasoning
11/20
Coding
14/20
Instruction
14/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View qwen2.5vl:3b details | View mlx-community/meta… 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