winnow-12b
LM-STUDIO GGUFgemma4 · 12B · Q8_0
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
liquid/lfm2-24b-a2b
LM-STUDIO MLXlfm2_moe · 24B · 4bit
Mar 19, 2026 · Apple M4
Global Score
77 vs 74
Hardware Fit
38 vs 84
Quality Score
93 vs 69
Hardware
winnow-12b liquid/lfm2-24b-a2b
MachineGMKtec EVO-X3Mac mini
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM120 GB24 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M4
OSMicrosoft Windows 11 Pro 10.0.26300macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
winnow-12b liquid/lfm2-24b-a2b
Tokens/sec12.958.9
First chunk19 ms28 ms
TTFT9.7 s481 ms
Load time86.2 sN/A
Memory usage51.3 GB17.5 GB
Memory %43%73%
HW Fit Score Breakdown
winnow-12b
Speed
11/50
TTFT
0/20
Memory
27/30
liquid/lfm2-24b-a2b
Speed
50/50
TTFT
20/20
Memory
14/30
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
liquid/lfm2-24b-a2b
Reasoning
11/20
Coding
12/20
Instruction
16/20
Structured
13/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate 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