gemma4:latest
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Jul 11, 2026 · AMD Ryzen 9 9950X 16-Core Processor
lfm2.5:8b
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
87 vs 80
Hardware Fit
75 vs 95
Quality Score
92 vs 73
Hardware
gemma4:latest lfm2.5:8b
MachineMicro-Star International Co., Ltd. MS-7E47MacBook Pro
CPUAMD Ryzen 9 9950X 16-Core ProcessorApple M1 Pro
Cores3210
RAM125 GB16 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 4080 SUPERApple M1 Pro
OSMicrosoft Windows 11 Pro 10.0.26100macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
gemma4:latest lfm2.5:8b
Tokens/sec42.498.5
First chunk472 ms167 ms
TTFT3.8 s2.5 s
Load time0.3 s3.0 s
Memory usage12.3 GB6.0 GB
Memory %10%37%
HW Fit Score Breakdown
gemma4:latest
Speed
40/50
TTFT
5/20
Memory
30/30
lfm2.5:8b
Speed
50/50
TTFT
17/20
Memory
28/30
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
lfm2.5:8b
Reasoning
2/20
Coding
12/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate 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