liquid/lfm2-1.2b
LM-STUDIO GGUFlfm2 · 1.2B · Q8_0
Oct 1, 2026 · AMD Ryzen 7 4800H
qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 20, 2026 · Apple M2 Max
Global Score
69 vs 97
Hardware Fit
100 vs 95
Quality Score
56 vs 98
Hardware
liquid/lfm2-1.2b qwen3-30b-a3b-thin…
MachineASUSTeK COMPUTER INC. ROG Strix G513IM_G513IMMac Studio
CPUAMD Ryzen 7 4800HApple M2 Max
Cores1612
RAM15 GB96 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPUApple M2 Max
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.1
Archx64arm64
Power Modebalancedbalanced
Performance
liquid/lfm2-1.2b qwen3-30b-a3b-thin…
Tokens/sec169.579.6
First chunk27 ms11 ms
TTFT77 ms1.7 s
Load timeN/A7.1 s
Memory usage3.4 GB0.0 GB
Memory %22%0%
HW Fit Score Breakdown
liquid/lfm2-1.2b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
15/20
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
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
19/20
Instruction
20/20
Structured
15/15
Math
15/15
Multilingual
10/10
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