Back to leaderboard

phi4-mini:latest

OLLAMA GGUF

phi3 · 3.8B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

qwen3-vl:30b

OLLAMA GGUF

qwen3vlmoe · 31.1B · Q4_K_M

Excellent

Mar 5, 2026 · Intel Core™ Ultra 9 285K

Global Score
71 vs 80
Hardware Fit
100 vs 98
Quality Score
58 vs 72

Hardware

phi4-mini:latest qwen3-vl:30b
MachineMacBook AirASUS
CPUApple M4Intel Core™ Ultra 9 285K
Cores1024
RAM32 GB47 GB
GPUApple M4NVIDIA GeForce RTX 5090, Intel(R) Graphics
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

phi4-mini:latest qwen3-vl:30b
Tokens/sec36.2208.9
First chunkN/A102 ms
TTFT190 ms684 ms
Load time0.8 s0.1 s
Memory usage8.3 GB22.0 GB
Memory %26%47%

HW Fit Score Breakdown

phi4-mini:latest

Speed
40/50
TTFT
30/20
Memory
30/30

qwen3-vl:30b

Speed
50/50
TTFT
20/20
Memory
28/30

Quality

phi4-mini:latest

Reasoning
12/20
Coding
10/20
Instruction
10/20
Structured
11/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Strong

qwen3-vl:30b

Reasoning
14/20
Coding
6/20
Instruction
17/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Strong 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