winnow-12b
LM-STUDIO GGUFgemma4 · 12B · Q8_0
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
orcarouter/Qwen3.8-27B-Uncensored:iq4_xs
OLLAMA GGUFqwen35 · 27.3B · IQ4_XS
Sep 11, 2026 · Intel Core™ i5-10400
Global Score
77 vs 88
Hardware Fit
38 vs 69
Quality Score
93 vs 96
Hardware
winnow-12b orcarouter/Qwen3.8…
MachineGMKtec EVO-X3ASUS
CPUAMD RYZEN AI MAX+ 395Intel Core™ i5-10400
Cores3212
RAM120 GB16 GB
GPUAMD Radeon(TM) 8060S GraphicsTodesk Virtual Display Adapter, AskLink Display Adapter (SDR), OrayIddDriver Device, NVIDIA GeForce RTX 3080
OSMicrosoft Windows 11 Pro 10.0.26300Microsoft Windows 10 专业版 10.0.19045
Archx64x64
Power Modebalancedbalanced
Performance
winnow-12b orcarouter/Qwen3.8…
Tokens/sec12.939.5
First chunk19 ms220 ms
TTFT9.7 s3.2 s
Load time86.2 s13.7 s
Memory usage51.3 GB14.2 GB
Memory %43%89%
HW Fit Score Breakdown
winnow-12b
Speed
11/50
TTFT
0/20
Memory
27/30
orcarouter/Qwen3.8-27B-…
Speed
50/50
TTFT
14/20
Memory
5/30
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
orcarouter/Qwen3.8-27B-…
Reasoning
19/20
Coding
19/20
Instruction
18/20
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