llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
Global Score
63 vs 73
Hardware Fit
100 vs 93
Quality Score
47 vs 65
Hardware
llama3.2:1b lfm2.5:latest
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperLENOVO 20L7CTO1WW
CPUCortex-A78AEIntel Core™ i5-8350U
Cores68
RAM7 GB23 GB
GPUIntegrated / UnknownKaby Lake-R GT2 [UHD Graphics 620]
OSUbuntu 22.04.5 LTSFedora Linux 44
Archarm64x64
Power Modebalancedperformance
Performance
llama3.2:1b lfm2.5:latest
Tokens/sec40.218.3
First chunk1087 ms981 ms
TTFT1.1 s981 ms
Load time6.2 s8.0 s
Memory usage1.4 GB4.9 GB
Memory %19%21%
HW Fit Score Breakdown
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
30/30
lfm2.5:latest
Speed
43/50
TTFT
20/20
Memory
30/30
Quality
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
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