qwen3-vl:4b-instruct
OLLAMA GGUFqwen3vl · 4.4B · Q4_K_M
Apr 20, 2026 · Apple M2 Max
gemma4:e4b
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
83 vs 84
Hardware Fit
96 vs 98
Quality Score
78 vs 78
Hardware
qwen3-vl:4b-instruct gemma4:e4b
MachineMac StudioAZW GTR Pro
CPUApple M2 MaxAMD RYZEN AI MAX+ 395
Cores1232
RAM96 GB125 GB
GPUApple M2 MaxRadeon 8060S
OSmacOS 26.1Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance
Performance
qwen3-vl:4b-instruct gemma4:e4b
Tokens/sec91.253.0
First chunk150 ms214 ms
TTFT150 ms214 ms
Load time5.3 s3.1 s
Memory usage42.5 GB15.0 GB
Memory %44%12%
HW Fit Score Breakdown
qwen3-vl:4b-instruct
Speed
50/50
TTFT
20/20
Memory
26/30
gemma4:e4b
Speed
48/50
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
gemma4:e4b
Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest