Gemma4-31B:31B
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Aug 18, 2026 · Intel Core™ Ultra X7 358H
qwen3.5:2b
OLLAMA GGUFqwen35 · 2.3B · Q8_0
Mar 2, 2026 · Apple M4
Global Score
76 vs 73
Hardware Fit
45 vs 100
Quality Score
89 vs 62
Hardware
Gemma4-31B:31B qwen3.5:2b
MachineGMKtec NucBox EVO-T2SMacBook Air
CPUIntel Core™ Ultra X7 358HApple M4
Cores1610
RAM64 GB32 GB
GPUIntel(R) Arc(TM) B390 GPUApple M4
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
Gemma4-31B:31B qwen3.5:2b
Tokens/sec3.830.4
First chunk3536 msN/A
TTFT3.5 s215 ms
Load time19.6 s1.8 s
Memory usage19.9 GB4.5 GB
Memory %31%14%
HW Fit Score Breakdown
Gemma4-31B:31B
Speed
5/50
TTFT
10/20
Memory
30/30
qwen3.5:2b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
Gemma4-31B:31B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
14/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.5:2b
Reasoning
12/20
Coding
10/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak 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