winnow-12b
LM-STUDIO GGUFgemma4 · 12B · Q8_0
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
Qwen3-30B:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Global Score
77 vs 91
Hardware Fit
38 vs 98
Quality Score
93 vs 88
Hardware
winnow-12b Qwen3-30B:30b
MachineGMKtec EVO-X3HP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUAMD RYZEN AI MAX+ 395NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores3220
RAM120 GB55 GB
GPUAMD Radeon(TM) 8060S GraphicsNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSMicrosoft Windows 11 Pro 10.0.26300Microsoft Windows 11 Pro 10.0.28000
Archx64arm64
Power Modebalancedbalanced
Performance
winnow-12b Qwen3-30B:30b
Tokens/sec12.980.5
First chunk19 ms158 ms
TTFT9.7 s158 ms
Load time86.2 s21.8 s
Memory usage51.3 GB20.3 GB
Memory %43%37%
HW Fit Score Breakdown
winnow-12b
Speed
11/50
TTFT
0/20
Memory
27/30
Qwen3-30B:30b
Speed
50/50
TTFT
20/20
Memory
28/30
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
Qwen3-30B:30b
Reasoning
16/20
Coding
19/20
Instruction
17/20
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