llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
lfm2.5:8b
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
63 vs 80
Hardware Fit
100 vs 95
Quality Score
47 vs 73
Hardware
llama3.2:1b lfm2.5:8b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M1 Pro
Cores610
RAM7 GB16 GB
GPUIntegrated / UnknownApple M1 Pro
OSUbuntu 22.04.5 LTSmacOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
llama3.2:1b lfm2.5:8b
Tokens/sec40.298.5
First chunk1087 ms167 ms
TTFT1.1 s2.5 s
Load time6.2 s3.0 s
Memory usage1.4 GB6.0 GB
Memory %19%37%
HW Fit Score Breakdown
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
30/30
lfm2.5:8b
Speed
50/50
TTFT
17/20
Memory
28/30
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
lfm2.5:8b
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