Back to leaderboard

qwen3-5-4b-q4-k-m

OLLAMA GGUF

llama · 4B · Q4_K_M

Excellent

Jul 9, 2026 · Intel Core™ i5-10400

liquid/lfm2-1.2b

LM-STUDIO GGUF

lfm2 · 1.2B · Q8_0

Good

Oct 1, 2026 · AMD Ryzen 7 4800H

Global Score
83 vs 69
Hardware Fit
100 vs 100
Quality Score
76 vs 56

Hardware

qwen3-5-4b-q4-k-m liquid/lfm2-1.2b
MachineMac ProASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM
CPUIntel Core™ i5-10400AMD Ryzen 7 4800H
Cores1216
RAM32 GB15 GB
GPUAMD Radeon RX 6700 XTAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU
OSmacOS 26.5.1Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen3-5-4b-q4-k-m liquid/lfm2-1.2b
Tokens/sec62.7169.5
First chunk278 ms27 ms
TTFT278 ms77 ms
Load time0.0 sN/A
Memory usage0.0 GB3.4 GB
Memory %0%22%

HW Fit Score Breakdown

qwen3-5-4b-q4-k-m

Speed
50/50
TTFT
20/20
Memory
30/30

liquid/lfm2-1.2b

Speed
50/50
TTFT
20/20
Memory
30/30

Quality

qwen3-5-4b-q4-k-m

Reasoning
14/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong 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
View qwen3-5-4b-q4-k-m details | View liquid/lfm2-1.2b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest