lfm2.5:latest

lfm2moe · 8.5B · Q4_K_M

THINKING MODEL ECO MODE

AZW GTR Pro (AMD RYZEN AI MAX+ 395)

125 GB · Ubuntu 24.04.4 LTS

Tested on June 20, 2026

Top 31% Compare

Global Score

79 /100

Good

Hardware Fit

100/100

Quality

70/100

Get this model

🦙

Ollama

ollama pull lfm2.5:latest

View on Ollama Library

ollama.com/library/lfm2.5

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: AZW GTR Pro
CPU: AMD RYZEN AI MAX+ 395
Cores: 32 threads (16 cores)
Frequency: 3 GHz
RAM: 125 GB
GPU: Radeon 8060S
OS: Ubuntu 24.04.4 LTS
Arch: x64
Power Mode: low-power

Performance

Tokens/sec Tokens generated per second — higher is better: 134.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.4
First chunk latency Delay before the first streamed chunk arrives from runtime: 226 ms
Time to first token How fast the model starts responding — lower is better: 226 ms
Load time Time to load the model into memory before inference: 1.8 s
Memory usage RAM consumed during inference — percentage of total system memory: 6.9 GB (6%)
Total tokens Total number of tokens generated across all benchmark prompts: 1423

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

2/20

Coding

11/20

Instruction following

17/20

Structured output

15/15

Math

15/15

Multilingual

10/10

Category levels

Reasoning: Poor Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.30.10
Model format: GGUF
Hardware profile: HIGH-END
Result hash: 967941402870d02b21d57e1cb8e40433f3183920062391221dc6d20817bf89c7

Interpretation

Hardware fit: 100/100. Overall suitability: GOOD (Global 79/100). Category profile: Reasoning: Poor, Coding: Adequate, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Warnings

System was in low-power mode during this benchmark.
CPU appears throttled (2.3 GHz current vs 3.0 GHz nominal, 76%).

Bench Environment

Thermal: nominal CPU load: avg 5% (peak 6%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest