llama3.2:latest
OLLAMA GGUFllama · 3.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
Global Score
76 vs 73
Hardware Fit
100 vs 93
Quality Score
65 vs 65
Hardware
llama3.2:latest lfm2.5:latest
MachineMicro-Star International Co., Ltd. MS-7B79LENOVO 20L7CTO1WW
CPUAMD Ryzen 5 2600X Six-Core ProcessorIntel Core™ i5-8350U
Cores128
RAM16 GB23 GB
GPUNVIDIA GeForce GTX 1080Kaby Lake-R GT2 [UHD Graphics 620]
OSMicrosoft Windows 11 Famille 10.0.26200Fedora Linux 44
Archx64x64
Power Modebalancedperformance
Performance
llama3.2:latest lfm2.5:latest
Tokens/sec57.018.3
First chunk264 ms981 ms
TTFT264 ms981 ms
Load time9.7 s8.0 s
Memory usage2.6 GB4.9 GB
Memory %16%21%
HW Fit Score Breakdown
llama3.2:latest
Speed
50/50
TTFT
20/20
Memory
30/30
lfm2.5:latest
Speed
43/50
TTFT
20/20
Memory
30/30
Quality
llama3.2:latest
Reasoning
11/20
Coding
15/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
lfm2.5:latest
Reasoning
2/20
Coding
11/20
Instruction
14/20
Structured
13/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate 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