gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
Global Score
78 vs 58
Hardware Fit
47 vs 82
Quality Score
92 vs 48
Hardware
gemma4:31b qwen3:14b
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M1 Max
Cores3210
RAM125 GB32 GB
GPURadeon 8060SApple M1 Max
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
gemma4:31b qwen3:14b
Tokens/sec9.824.4
First chunk873 ms294 ms
TTFT873 ms7.9 s
Load time7.0 s3.7 s
Memory usage68.3 GB13.8 GB
Memory %55%43%
HW Fit Score Breakdown
gemma4:31b
Speed
8/50
TTFT
16/20
Memory
23/30
qwen3:14b
Speed
47/50
TTFT
5/20
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
qwen3:14b
Reasoning
13/20
Coding
6/20
Instruction
10/20
Structured
9/15
Math
2/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate 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