gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
hermes3:8b
OLLAMA GGUFllama · 8.0B · Q4_0
Mar 6, 2026 · Apple M4
Global Score
78 vs 74
Hardware Fit
47 vs 94
Quality Score
92 vs 65
Hardware
gemma4:31b hermes3:8b
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 hermes3:8b
Tokens/sec9.822.3
First chunk873 ms296 ms
TTFT873 ms296 ms
Load time7.0 s0.8 s
Memory usage68.3 GB10.2 GB
Memory %55%32%
HW Fit Score Breakdown
gemma4:31b
Speed
8/50
TTFT
16/20
Memory
23/30
hermes3:8b
Speed
44/50
TTFT
20/20
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
hermes3:8b
Reasoning
11/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate 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