winnow-12b
LM-STUDIO GGUFgemma4 · 12B · Q8_0
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
qwen3-coder:30b-a3b-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 18, 2026 · Intel Core™ Ultra 9 285HX
Global Score
77 vs 91
Hardware Fit
38 vs 100
Quality Score
93 vs 87
Hardware
winnow-12b qwen3-coder:30b-a3…
MachineGMKtec EVO-X3Micro-Star International Co., Ltd. Titan 18 HX AI A2XWJG
CPUAMD RYZEN AI MAX+ 395Intel Core™ Ultra 9 285HX
Cores3224
RAM120 GB63 GB
GPUAMD Radeon(TM) 8060S GraphicsIntel(R) Graphics, NVIDIA GeForce RTX 5090 Laptop GPU
OSMicrosoft Windows 11 Pro 10.0.26300Microsoft Windows 11 Home Single Language 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
winnow-12b qwen3-coder:30b-a3…
Tokens/sec12.9175.3
First chunk19 ms224 ms
TTFT9.7 s224 ms
Load time86.2 s6.1 s
Memory usage51.3 GB18.7 GB
Memory %43%30%
HW Fit Score Breakdown
winnow-12b
Speed
11/50
TTFT
0/20
Memory
27/30
qwen3-coder:30b-a3b-q4_…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
winnow-12b
Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-coder:30b-a3b-q4_…
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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