winnow-12b
LM-STUDIO GGUFgemma4 · 12B · Q8_0
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
77 vs 76
Hardware Fit
38 vs 89
Quality Score
93 vs 71
Hardware
winnow-12b ministral-3:8b
MachineGMKtec EVO-X3MacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM120 GB32 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M4
OSMicrosoft Windows 11 Pro 10.0.26300macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
winnow-12b ministral-3:8b
Tokens/sec12.919.5
First chunk19 ms328 ms
TTFT9.7 s328 ms
Load time86.2 s1.5 s
Memory usage51.3 GB10.6 GB
Memory %43%33%
HW Fit Score Breakdown
winnow-12b
Speed
11/50
TTFT
0/20
Memory
27/30
ministral-3:8b
Speed
39/50
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
ministral-3:8b
Reasoning
12/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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