gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
qwen3-coder:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Global Score
76 vs 76
Hardware Fit
46 vs 51
Quality Score
89 vs 87
Hardware
gemma4:31b qwen3-coder:latest
MachineMacBook ProDell Inc. Inspiron 15 3530
CPUApple M4 MaxIntel Gen Intel® Core™ i7-1355U
Cores1612
RAM64 GB31 GB
GPUApple M4 MaxRaptor Lake-P [Iris Xe Graphics]
OSmacOS 26.3.1cachyos rolling
Archarm64x64
Power Modebalancedlow-power
Performance
gemma4:31b qwen3-coder:latest
Tokens/sec22.47.6
First chunk565 ms2037 ms
TTFT30.0 s2.0 s
Load time6.9 s8.7 s
Memory usage43.9 GB18.9 GB
Memory %69%61%
HW Fit Score Breakdown
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
qwen3-coder:latest
Speed
13/50
TTFT
18/20
Memory
20/30
Quality
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
qwen3-coder:latest
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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