Back to leaderboard

winnow-12b

LM-STUDIO GGUF

gemma4 · 12B · Q8_0

Good

Nov 1, 2026 · AMD RYZEN AI MAX+ 395

gemma-4-31b-it-mlx

LM-STUDIO MLX

gemma4 · 31B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

Global Score
77 vs 85
Hardware Fit
38 vs 64
Quality Score
93 vs 94

Hardware

winnow-12b gemma-4-31b-it-mlx
MachineGMKtec EVO-X3MacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M4 Max
Cores3216
RAM120 GB128 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M4 Max
OSMicrosoft Windows 11 Pro 10.0.26300macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced

Performance

winnow-12b gemma-4-31b-it-mlx
Tokens/sec12.913.6
First chunk19 ms16 ms
TTFT9.7 s558 ms
Load time86.2 s12.3 s
Memory usage51.3 GB0.0 GB
Memory %43%0%

HW Fit Score Breakdown

winnow-12b

Speed
11/50
TTFT
0/20
Memory
27/30

gemma-4-31b-it-mlx

Speed
14/50
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

gemma-4-31b-it-mlx

Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View winnow-12b details | View gemma-4-31b-it-mlx details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest