qwen/qwen3.6-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
spark-x2.5-4b
LM-STUDIO GGUFspark2_5 · 4B · Q4_K_M
Sep 30, 2026 · AMD Ryzen 7 4800H
Global Score
88 vs 77
Hardware Fit
90 vs 90
Quality Score
87 vs 71
Hardware
qwen/qwen3.6-35b-a3b spark-x2.5-4b
MachineGMKtec EVO-X3ASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 7 4800H
Cores3216
RAM120 GB15 GB
GPUAMD Radeon(TM) 8060S GraphicsAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU
OSMicrosoft Windows 11 Pro 10.0.26300Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
qwen/qwen3.6-35b-a3b spark-x2.5-4b
Tokens/sec49.048.9
First chunk44 ms20 ms
TTFT334 ms168 ms
Load time61.3 sN/A
Memory usage59.8 GB9.4 GB
Memory %50%61%
HW Fit Score Breakdown
qwen/qwen3.6-35b-a3b
Speed
45/50
TTFT
20/20
Memory
25/30
spark-x2.5-4b
Speed
50/50
TTFT
20/20
Memory
20/30
Quality
qwen/qwen3.6-35b-a3b
Reasoning
16/20
Coding
18/20
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
spark-x2.5-4b
Reasoning
13/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong 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