gemma4:latest
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Jul 11, 2026 · AMD Ryzen 9 9950X 16-Core Processor
llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
Global Score
87 vs 63
Hardware Fit
75 vs 100
Quality Score
92 vs 47
Hardware
gemma4:latest llama3.2:1b
MachineMicro-Star International Co., Ltd. MS-7E47NVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUAMD Ryzen 9 9950X 16-Core ProcessorCortex-A78AE
Cores326
RAM125 GB7 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 4080 SUPERIntegrated / Unknown
OSMicrosoft Windows 11 Pro 10.0.26100Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced
Performance
gemma4:latest llama3.2:1b
Tokens/sec42.440.2
First chunk472 ms1087 ms
TTFT3.8 s1.1 s
Load time0.3 s6.2 s
Memory usage12.3 GB1.4 GB
Memory %10%19%
HW Fit Score Breakdown
gemma4:latest
Speed
40/50
TTFT
5/20
Memory
30/30
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gemma4:latest
Reasoning
19/20
Coding
18/20
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
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