gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · Apple M4
llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
Global Score
85 vs 63
Hardware Fit
77 vs 100
Quality Score
89 vs 47
Hardware
gemma4:26b llama3.2:1b
MachineMac miniNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4Cortex-A78AE
Cores106
RAM24 GB7 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:26b llama3.2:1b
Tokens/sec24.540.2
First chunk1481 ms1087 ms
TTFT1.5 s1.1 s
Load time24.7 s6.2 s
Memory usage20.3 GB1.4 GB
Memory %85%19%
HW Fit Score Breakdown
gemma4:26b
Speed
49/50
TTFT
20/20
Memory
8/30
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gemma4:26b
Reasoning
17/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
llama3.2:1b
Reasoning
4/20
Coding
9/20
Instruction
14/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong 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