gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
qwen3.5-2b-mlx
LM-STUDIO MLXqwen3_5 · 2B · 8bit
Mar 3, 2026 · Apple M4
Global Score
78 vs 70
Hardware Fit
47 vs 93
Quality Score
92 vs 60
Hardware
gemma4:31b qwen3.5-2b-mlx
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 qwen3.5-2b-mlx
Tokens/sec9.832.9
First chunk873 ms3096 ms
TTFT873 ms3.1 s
Load time7.0 sN/A
Memory usage68.3 GB2.5 GB
Memory %55%8%
HW Fit Score Breakdown
gemma4:31b
Speed
8/50
TTFT
16/20
Memory
23/30
qwen3.5-2b-mlx
Speed
50/50
TTFT
13/20
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
qwen3.5-2b-mlx
Reasoning
11/20
Coding
9/20
Instruction
14/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate 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