qwen3.6:35b-a3b
OLLAMA GGUFqwen35moe · 35.5B · 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
87 vs 100
Quality Score
86 vs 56
Hardware
qwen3.6:35b-a3b 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
qwen3.6:35b-a3b liquid/lfm2-1.2b
Tokens/sec59.5169.5
First chunk380 ms27 ms
TTFT380 ms77 ms
Load time24.6 sN/A
Memory usage20.9 GB3.4 GB
Memory %66%22%
HW Fit Score Breakdown
qwen3.6:35b-a3b
Speed
50/50
TTFT
20/20
Memory
17/30
liquid/lfm2-1.2b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.6:35b-a3b
Reasoning
16/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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