lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 20, 2026 · AMD RYZEN AI MAX+ 395
llama2:13b
OLLAMA GGUFllama · 13B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
79 vs 56
Hardware Fit
100 vs 84
Quality Score
70 vs 44
Hardware
lfm2.5:latest llama2:13b
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB32 GB
GPURadeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
lfm2.5:latest llama2:13b
Tokens/sec134.413.5
First chunk226 msN/A
TTFT226 ms415 ms
Load time1.8 s0.6 s
Memory usage6.9 GB10.3 GB
Memory %6%32%
HW Fit Score Breakdown
lfm2.5:latest
Speed
50/50
TTFT
20/20
Memory
30/30
llama2:13b
Speed
24/50
TTFT
30/20
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
llama2:13b
Reasoning
9/20
Coding
3/20
Instruction
13/20
Structured
7/15
Math
3/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Poor 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