gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
vicuna:13b
OLLAMA GGUFllama · 13B · Q4_0
Mar 1, 2026 · Apple M4
Global Score
78 vs 59
Hardware Fit
47 vs 84
Quality Score
92 vs 48
Hardware
gemma4:31b vicuna:13b
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB32 GB
GPURadeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
gemma4:31b vicuna:13b
Tokens/sec9.813.4
First chunk873 msN/A
TTFT873 ms438 ms
Load time7.0 s0.6 s
Memory usage68.3 GB10.3 GB
Memory %55%32%
HW Fit Score Breakdown
gemma4:31b
Speed
8/50
TTFT
16/20
Memory
23/30
vicuna:13b
Speed
24/50
TTFT
30/20
Memory
30/30
Quality
gemma4:31b
Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
vicuna:13b
Reasoning
7/20
Coding
5/20
Instruction
12/20
Structured
13/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor 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