qwen3.5:2b
OLLAMA GGUFqwen35 · 2.3B · Q8_0
Apr 29, 2026 · Intel Core™ i5-8350U
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jul 4, 2026 · Apple M2 Pro
Global Score
13 vs 89
Hardware Fit
41 vs 88
Quality Score
1 vs 89
Hardware
qwen3.5:2b gemma4:12b
MachineLENOVO 20L7CTO1WWMacBook Pro
CPUIntel Core™ i5-8350UApple M2 Pro
Cores810
RAM23 GB16 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M2 Pro
OSFedora Linux 43macOS 26.5
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3.5:2b gemma4:12b
Tokens/sec4.518.5
First chunk1413 ms752 ms
TTFT31.1 s752 ms
Load time7.1 s6.1 s
Memory usage3.8 GB7.5 GB
Memory %16%47%
HW Fit Score Breakdown
qwen3.5:2b
Speed
11/50
TTFT
0/20
Memory
30/30
gemma4:12b
Speed
42/50
TTFT
20/20
Memory
26/30
Quality
qwen3.5:2b
Reasoning
0/20
Coding
0/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
gemma4:12b
Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
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