liquid/lfm2-1.2b
LM-STUDIO GGUFlfm2 · 1.2B · Q8_0
Oct 1, 2026 · AMD Ryzen 7 4800H
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
69 vs 86
Hardware Fit
100 vs 78
Quality Score
56 vs 89
Hardware
liquid/lfm2-1.2b Kimi-48B:48B
MachineASUSTeK COMPUTER INC. ROG Strix G513IM_G513IMGMKtec NucBox EVO-T2S
CPUAMD Ryzen 7 4800HIntel Core™ Ultra X7 358H
Cores1616
RAM15 GB64 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPUIntel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
liquid/lfm2-1.2b Kimi-48B:48B
Tokens/sec169.522.8
First chunk27 ms721 ms
TTFT77 ms721 ms
Load timeN/A23.0 s
Memory usage3.4 GB25.5 GB
Memory %22%40%
HW Fit Score Breakdown
liquid/lfm2-1.2b
Speed
50/50
TTFT
20/20
Memory
30/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
liquid/lfm2-1.2b
Reasoning
9/20
Coding
7/20
Instruction
14/20
Structured
12/15
Math
5/15
Multilingual
9/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
Kimi-48B:48B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong 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