lfm2:24b
OLLAMA GGUFlfm2moe · 23.8B · Q4_K_M
Mar 27, 2026 · AMD RYZEN AI MAX+ 395
llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
88 vs 46
Hardware Fit
100 vs 61
Quality Score
83 vs 40
Hardware
lfm2:24b llama3.1:8b
MachineAZW GTR ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUAMD RYZEN AI MAX+ 395Cortex-A78AE
Cores326
RAM125 GB7 GB
GPURadeon 8060SIntegrated / Unknown
OSUbuntu 24.04.4 LTSUbuntu 22.04.5 LTS
Archx64arm64
Power Modeperformancebalanced
Performance
lfm2:24b llama3.1:8b
Tokens/sec95.47.8
First chunk202 ms1625 ms
TTFT202 ms1.6 s
Load time5.0 s21.8 s
Memory usage14.3 GB5.2 GB
Memory %12%71%
HW Fit Score Breakdown
lfm2:24b
Speed
50/50
TTFT
20/20
Memory
30/30
llama3.1:8b
Speed
26/50
TTFT
20/20
Memory
15/30
Quality
lfm2:24b
Reasoning
14/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
llama3.1:8b
Reasoning
12/20
Coding
10/20
Instruction
4/20
Structured
1/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor 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