qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
gemma-2-2b-it
LM-STUDIO GGUFgemma2 · 2B · Q4_K_M
Mar 6, 2026 · Intel Core™ i5-5300U
Global Score
53 vs 58
Hardware Fit
72 vs 50
Quality Score
45 vs 62
Hardware
qwen3.5:9b gemma-2-2b-it
MachineMacBook ProLENOVO 20BUS00700
CPUApple M1 MaxIntel Core™ i5-5300U
Cores104
RAM32 GB16 GB
GPUApple M1 MaxIntel(R) HD Graphics 5500
OSmacOS 26.3Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.5:9b gemma-2-2b-it
Tokens/sec18.63.6
First chunk403 ms4509 ms
TTFT10.2 s4.5 s
Load time4.3 sN/A
Memory usage9.1 GB1.6 GB
Memory %28%10%
HW Fit Score Breakdown
qwen3.5:9b
Speed
38/50
TTFT
4/20
Memory
30/30
gemma-2-2b-it
Speed
14/50
TTFT
12/20
Memory
24/30
Quality
qwen3.5:9b
Reasoning
12/20
Coding
3/20
Instruction
5/20
Structured
6/15
Math
11/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong
gemma-2-2b-it
Reasoning
11/20
Coding
8/20
Instruction
14/20
Structured
15/15
Math
4/15
Multilingual
10/10
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