qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 2, 2026 · Apple M4
gemma4:e4b-it-q8_0
OLLAMA GGUFgemma4 · 8.0B · Q8_0
Aug 26, 2026 · Apple M1 Pro
Global Score
80 vs 91
Hardware Fit
81 vs 88
Quality Score
80 vs 92
Hardware
qwen3.5:9b gemma4:e4b-it-q8_0
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:9b gemma4:e4b-it-q8_0
Tokens/sec11.830.0
First chunkN/A311 ms
TTFT523 ms6.2 s
Load time2.9 s6.9 s
Memory usage9.1 GB5.0 GB
Memory %28%31%
HW Fit Score Breakdown
qwen3.5:9b
Speed
21/50
TTFT
30/20
Memory
30/30
gemma4:e4b-it-q8_0
Speed
50/50
TTFT
8/20
Memory
30/30
Quality
qwen3.5:9b
Reasoning
14/20
Coding
16/20
Instruction
15/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
gemma4:e4b-it-q8_0
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
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