Back to leaderboard

qwen3-vl:4b-instruct

OLLAMA GGUF

qwen3vl · 4.4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

qwen2.5-coder:14b

OLLAMA GGUF

qwen2 · 14.8B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score
83 vs 86
Hardware Fit
96 vs 100
Quality Score
78 vs 80

Hardware

qwen3-vl:4b-instruct qwen2.5-coder:14b
MachineMac StudioGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUApple M2 MaxIntel Core™ i5-14400F
Cores1216
RAM96 GB32 GB
GPUApple M2 MaxNVIDIA GeForce RTX 5060 Ti
OSmacOS 26.1Microsoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-vl:4b-instruct qwen2.5-coder:14b
Tokens/sec90.638.3
First chunk159 ms78 ms
TTFT159 ms78 ms
Load time5.8 s6.3 s
Memory usage42.5 GB8.8 GB
Memory %44%28%

HW Fit Score Breakdown

qwen3-vl:4b-instruct

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

qwen2.5-coder:14b

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

Quality

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

qwen2.5-coder:14b

Reasoning
14/20
Coding
18/20
Instruction
14/20
Structured
13/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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