winnow-12b
LM-STUDIO GGUFgemma4 · 12B · Q8_0
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
qwen3.5-35b-a3b-t48-c8k:latest
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Sep 6, 2026 · Intel Xeon® E5-4650 v2
Global Score
77 vs 81
Hardware Fit
38 vs 63
Quality Score
93 vs 88
Hardware
winnow-12b qwen3.5-35b-a3b-t4…
MachineGMKtec EVO-X3Dell Inc. PowerEdge R820
CPUAMD RYZEN AI MAX+ 395Intel Xeon® E5-4650 v2
Cores3280
RAM120 GB256 GB
GPUAMD Radeon(TM) 8060S GraphicsMicrosoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display Adapter
OSMicrosoft Windows 11 Pro 10.0.26300Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modebalancedbalanced
Performance
winnow-12b qwen3.5-35b-a3b-t4…
Tokens/sec12.917.2
First chunk19 ms845 ms
TTFT9.7 s845 ms
Load time86.2 s103.1 s
Memory usage51.3 GB21.9 GB
Memory %43%9%
HW Fit Score Breakdown
winnow-12b
Speed
11/50
TTFT
0/20
Memory
27/30
qwen3.5-35b-a3b-t48-c8k…
Speed
16/50
TTFT
17/20
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
qwen3.5-35b-a3b-t48-c8k…
Reasoning
17/20
Coding
18/20
Instruction
16/20
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