qwen2.5-coder:14b
OLLAMA GGUFqwen2 · 14.8B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
liquid/lfm2-1.2b
LM-STUDIO GGUFlfm2 · 1.2B · Q8_0
Oct 1, 2026 · AMD Ryzen 7 4800H
Global Score
86 vs 69
Hardware Fit
100 vs 100
Quality Score
80 vs 56
Hardware
qwen2.5-coder:14b liquid/lfm2-1.2b
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4ASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM
CPUIntel Core™ i5-14400FAMD Ryzen 7 4800H
Cores1616
RAM32 GB15 GB
GPUNVIDIA GeForce RTX 5060 TiAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU
OSMicrosoft Windows 11 Professionnel 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
qwen2.5-coder:14b liquid/lfm2-1.2b
Tokens/sec38.3169.5
First chunk78 ms27 ms
TTFT78 ms77 ms
Load time6.3 sN/A
Memory usage8.8 GB3.4 GB
Memory %28%22%
HW Fit Score Breakdown
qwen2.5-coder:14b
Speed
50/50
TTFT
20/20
Memory
30/30
liquid/lfm2-1.2b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen2.5-coder:14b
Reasoning
14/20
Coding
18/20
Instruction
14/20
Structured
13/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
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
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