winnow-12b
LM-STUDIO GGUFgemma4 · 12B · Q8_0
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
qwen3-30b-a3b-t16-c32k-instruct:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 18, 2026 · Intel Xeon® E5-2637 v3
Global Score
77 vs 94
Hardware Fit
38 vs 100
Quality Score
93 vs 91
Hardware
winnow-12b qwen3-30b-a3b-t16-…
MachineGMKtec EVO-X3Dell Inc. Precision Tower 7910
CPUAMD RYZEN AI MAX+ 395Intel Xeon® E5-2637 v3
Cores3216
RAM120 GB96 GB
GPUAMD Radeon(TM) 8060S GraphicsNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSMicrosoft Windows 11 Pro 10.0.26300Microsoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modebalancedbalanced
Performance
winnow-12b qwen3-30b-a3b-t16-…
Tokens/sec12.9116.0
First chunk19 ms575 ms
TTFT9.7 s575 ms
Load time86.2 s10.2 s
Memory usage51.3 GB21.0 GB
Memory %43%22%
HW Fit Score Breakdown
winnow-12b
Speed
11/50
TTFT
0/20
Memory
27/30
qwen3-30b-a3b-t16-c32k-…
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
qwen3-30b-a3b-t16-c32k-…
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
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