liquid/lfm2-1.2b

LM-STUDIO GGUF

lfm2 · 1.2B · Q8_0

Good

Oct 1, 2026 · AMD Ryzen 7 4800H

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Excellent

Mar 5, 2026 · Apple M1 Max

Global Score

69 vs 83

Hardware Fit

100 vs 100

Quality Score

56 vs 76

Hardware

liquid/lfm2-1.2b qwen3.5:4b

MachineASUSTeK COMPUTER INC. ROG Strix G513IM_G513IMMacBook Pro

CPUAMD Ryzen 7 4800HApple M1 Max

Cores1610

RAM15 GB32 GB

GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPUApple M1 Max

OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3

Archx64arm64

Power Modebalancedbalanced

Performance

liquid/lfm2-1.2b qwen3.5:4b

Tokens/sec169.532.4

First chunk27 ms306 ms

TTFT77 ms306 ms

Load timeN/A2.7 s

Memory usage3.4 GB6.5 GB

Memory %22%20%

HW Fit Score Breakdown

liquid/lfm2-1.2b

Speed

50/50

TTFT

20/20

Memory

30/30

qwen3.5:4b

Speed

50/50

TTFT

20/20

Memory

30/30

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

qwen3.5:4b

Reasoning

16/20

Coding

14/20

Instruction

15/20

Structured

15/15

Math

7/15

Multilingual

9/10

Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

View liquid/lfm2-1.2b details | View qwen3.5:4b 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