qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Aug 23, 2026 · Apple M1 Pro
gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
69 vs 78
Hardware Fit
86 vs 47
Quality Score
62 vs 92
Hardware
qwen3.5:4b gemma4:31b
MachineMacBook ProAZW GTR Pro
CPUApple M1 ProAMD RYZEN AI MAX+ 395
Cores1032
RAM16 GB125 GB
GPUApple M1 ProRadeon 8060S
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance
Performance
qwen3.5:4b gemma4:31b
Tokens/sec36.79.8
First chunk207 ms873 ms
TTFT6.6 s873 ms
Load time3.0 s7.0 s
Memory usage5.3 GB68.3 GB
Memory %33%55%
HW Fit Score Breakdown
qwen3.5:4b
Speed
50/50
TTFT
7/20
Memory
29/30
gemma4:31b
Speed
8/50
TTFT
16/20
Memory
23/30
Quality
qwen3.5:4b
Reasoning
16/20
Coding
1/20
Instruction
14/20
Structured
9/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong Multilingual: Strong
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
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