qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
Global Score
65 vs 76
Hardware Fit
73 vs 46
Quality Score
62 vs 89
Hardware
qwen3.5:4b gemma4:31b
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M4 Max
Cores3216
RAM125 GB64 GB
GPUAMD Radeon 8060SApple M4 Max
OSUbuntu 24.04.4 LTSmacOS 26.3.1
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3.5:4b gemma4:31b
Tokens/sec45.722.4
First chunk180 ms565 ms
TTFT30.0 s30.0 s
Load time5.3 s6.9 s
Memory usage16.2 GB43.9 GB
Memory %13%69%
HW Fit Score Breakdown
qwen3.5:4b
Speed
43/50
TTFT
0/20
Memory
30/30
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
Quality
qwen3.5:4b
Reasoning
17/20
Coding
1/20
Instruction
13/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong Multilingual: Strong
gemma4:31b
Reasoning
16/20
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