granite3.1-moe:3b
OLLAMA GGUFgranitemoe · 3.3B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
lfm2.5:8b
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
66 vs 80
Hardware Fit
99 vs 95
Quality Score
52 vs 73
Hardware
granite3.1-moe:3b lfm2.5:8b
MachineDell Inc. Inspiron 15 3530MacBook Pro
CPUIntel Gen Intel® Core™ i7-1355UApple M1 Pro
Cores1210
RAM31 GB16 GB
GPURaptor Lake-P [Iris Xe Graphics]Apple M1 Pro
OScachyos rollingmacOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced
Performance
granite3.1-moe:3b lfm2.5:8b
Tokens/sec27.298.5
First chunk527 ms167 ms
TTFT527 ms2.5 s
Load time1.9 s3.0 s
Memory usage2.9 GB6.0 GB
Memory %9%37%
HW Fit Score Breakdown
granite3.1-moe:3b
Speed
49/50
TTFT
20/20
Memory
30/30
lfm2.5:8b
Speed
50/50
TTFT
17/20
Memory
28/30
Quality
granite3.1-moe:3b
Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
12/15
Math
5/15
Multilingual
6/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak 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