codegemma:7b
OLLAMA GGUFgemma · 9B · Q4_0
Mar 1, 2026 · Apple M4
gemma3:1b
OLLAMA GGUFgemma3 · 999.89M · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
Global Score
71 vs 57
Hardware Fit
91 vs 100
Quality Score
62 vs 39
Hardware
codegemma:7b gemma3:1b
MachineMacBook AirNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4Cortex-A78AE
Cores106
RAM32 GB7 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
codegemma:7b gemma3:1b
Tokens/sec18.733.7
First chunkN/A2039 ms
TTFT320 ms2.0 s
Load time0.8 s7.3 s
Memory usage8.7 GB0.8 GB
Memory %27%11%
HW Fit Score Breakdown
codegemma:7b
Speed
31/50
TTFT
30/20
Memory
30/30
gemma3:1b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
codegemma:7b
Reasoning
1/20
Coding
14/20
Instruction
13/20
Structured
15/15
Math
10/15
Multilingual
9/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
gemma3:1b
Reasoning
6/20
Coding
3/20
Instruction
14/20
Structured
8/15
Math
1/15
Multilingual
7/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate
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