lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 20, 2026 · AMD RYZEN AI MAX+ 395
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Oct 31, 2026 · Intel Gen Intel® Core™ i9-12900H
Global Score
79 vs 83
Hardware Fit
100 vs 100
Quality Score
70 vs 75
Hardware
lfm2.5:latest qwen3:8b
MachineAZW GTR ProMicro-Star International Co., Ltd. Stealth GS77 12UH
CPUAMD RYZEN AI MAX+ 395Intel Gen Intel® Core™ i9-12900H
Cores3220
RAM125 GB32 GB
GPURadeon 8060SIntel(R) Iris(R) Xe Graphics, NVIDIA GeForce RTX 3080 Laptop GPU
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Home 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
lfm2.5:latest qwen3:8b
Tokens/sec134.454.0
First chunk226 ms68 ms
TTFT226 ms68 ms
Load time1.8 s6.1 s
Memory usage6.9 GB5.8 GB
Memory %6%18%
HW Fit Score Breakdown
lfm2.5:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3:8b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
lfm2.5:latest
Reasoning
2/20
Coding
11/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:8b
Reasoning
15/20
Coding
15/20
Instruction
15/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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