Views
No views yet
| GGUF Link | Quantization | Description |
|---|---|---|
| Download | Q2_K | Lowest quality |
| Download | Q3_K_S | |
| Download | IQ3_S | Integer quant, preferable over Q3_K_S |
| Download | IQ3_M | Integer quant |
| Download | Q3_K_M | |
| Download | Q3_K_L | |
| Download | IQ4_XS | Integer quant |
| Download | Q4_K_S | Fast with good performance |
| Download | Q4_K_M | Recommended: Perfect mix of speed and performance |
| Download | Q5_K_S | |
| Download | Q5_K_M | |
| Download | Q6_K | Very good quality |
| Download | Q8_0 | Best quality |
| Download | f16 | Full precision, don't bother; use a quant |
1models:
2 - model: Novaciano/HDP-1B
3 parameters:
4 density: 0.38
5 weight: 0.55
6 - model: megabytes/gemma-3-1b-qat-int4-heretic
7 parameters:
8 density: 0.35
9 weight: 0.30
10
11merge_method: dare_ties # Más agresivo que TIES puro
12base_model: Novaciano/Esperpento-1B
13
14parameters:
15 normalize: false
16 rescale: true # Amplifica bias NSFW
17 int8_mask: true
18 density: 0.38 # Baja para más filo
19 lambda: -0.45 # Suprime moral residual
20
21dtype: float16