Back to leaderboard

qwen3-vl-4b-instruct-q4_k_m.gguf

OPENAI GGUF
Good

Apr 21, 2026 · Apple M2 Max

phi4:latest

OLLAMA GGUF

phi3 · 14.7B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score
62 vs 85
Hardware Fit
100 vs 100
Quality Score
46 vs 79

Hardware

qwen3-vl-4b-instru… phi4:latest
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-instru… phi4:latest
Tokens/sec67.838.3
First chunk62 ms72 ms
TTFT64 ms72 ms
Load time0.0 s6.2 s
Memory usage0.0 GB9.1 GB
Memory %0%29%

HW Fit Score Breakdown

qwen3-vl-4b-instruct-q4…

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

phi4:latest

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

Quality

qwen3-vl-4b-instruct-q4…

Reasoning
16/20
Coding
0/20
Instruction
12/20
Structured
1/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Poor Math: Adequate Multilingual: Strong

phi4:latest

Reasoning
18/20
Coding
19/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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