qwen3.8:27b
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Oct 3, 2026 · Cortex-X925
winnow-12b
LM-STUDIO GGUFgemma4 · 12B · Q8_0
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
Global Score
84 vs 77
Hardware Fit
66 vs 38
Quality Score
92 vs 93
Hardware
qwen3.8:27b winnow-12b
MachineNVIDIA NVIDIA_DGX_SparkGMKtec EVO-X3
CPUCortex-X925AMD RYZEN AI MAX+ 395
Cores2032
RAM122 GB120 GB
GPUDevice 2e12AMD Radeon(TM) 8060S Graphics
OSUbuntu 24.04.5 LTSMicrosoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modeperformancebalanced
Performance
qwen3.8:27b winnow-12b
Tokens/sec29.412.9
First chunk306 ms19 ms
TTFT4.8 s9.7 s
Load time5.3 s86.2 s
Memory usage16.2 GB51.3 GB
Memory %13%43%
HW Fit Score Breakdown
qwen3.8:27b
Speed
31/50
TTFT
5/20
Memory
30/30
winnow-12b
Speed
11/50
TTFT
0/20
Memory
27/30
Quality
qwen3.8:27b
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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
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