bartowski/Pantheon-RP-1.6-12b-Nemo-GGUF-torrent
bartowski/Pantheon-RP-1.6-12b-Nemo-GGUF · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
| Filename | Quant Type | File Size | Split | Description |
|---|---|---|---|---|
| Pantheon-RP-1.6-12b-Nemo-bf16.gguf | bf16 | 24.50GB | ❌ | Full BF16 weights. |
| Pantheon-RP-1.6-12b-Nemo-Q8_0.gguf | Q8_0 | 13.02GB | ❌ | Extremely high quality, generally unneeded but max available quant. |
| Pantheon-RP-1.6-12b-Nemo-Q6_K_L.gguf | Q6_K_L | 10.38GB | ❌ | Uses Q8_0 for embed and output weights. Very high quality, near perfect, recommended. |
| Pantheon-RP-1.6-12b-Nemo-Q6_K.gguf | Q6_K | 10.06GB | ❌ | Very high quality, near perfect, recommended. |
| Pantheon-RP-1.6-12b-Nemo-Q5_K_L.gguf | Q5_K_L | 9.14GB | ❌ | Uses Q8_0 for embed and output weights. High quality, recommended. |
| Pantheon-RP-1.6-12b-Nemo-Q5_K_M.gguf | Q5_K_M | 8.73GB | ❌ | High quality, recommended. |
| Pantheon-RP-1.6-12b-Nemo-Q5_K_S.gguf | Q5_K_S | 8.52GB | ❌ | High quality, recommended. |
| Pantheon-RP-1.6-12b-Nemo-Q4_K_L.gguf | Q4_K_L | 7.98GB | ❌ | Uses Q8_0 for embed and output weights. Good quality, recommended. |
| Pantheon-RP-1.6-12b-Nemo-Q4_K_M.gguf | Q4_K_M | 7.48GB | ❌ | Good quality, default size for most use cases, recommended. |
| Pantheon-RP-1.6-12b-Nemo-Q3_K_XL.gguf | Q3_K_XL | 7.15GB | ❌ | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| Pantheon-RP-1.6-12b-Nemo-Q4_K_S.gguf | Q4_K_S | 7.12GB | ❌ | Slightly lower quality with more space savings, recommended. |
| Pantheon-RP-1.6-12b-Nemo-IQ4_XS.gguf | IQ4_XS | 6.74GB | ❌ | Decent quality, smaller than Q4_K_S with similar performance, recommended. |
| Pantheon-RP-1.6-12b-Nemo-Q3_K_L.gguf | Q3_K_L | 6.56GB | ❌ | Lower quality but usable, good for low RAM availability. |
| Pantheon-RP-1.6-12b-Nemo-Q3_K_M.gguf | Q3_K_M | 6.08GB | ❌ | Low quality. |
| Pantheon-RP-1.6-12b-Nemo-IQ3_M.gguf | IQ3_M | 5.72GB | ❌ | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| Pantheon-RP-1.6-12b-Nemo-Q3_K_S.gguf | Q3_K_S | 5.53GB | ❌ | Low quality, not recommended. |
| Pantheon-RP-1.6-12b-Nemo-Q2_K_L.gguf | Q2_K_L | 5.45GB | ❌ | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| Pantheon-RP-1.6-12b-Nemo-IQ3_XS.gguf | IQ3_XS | 5.31GB | ❌ | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| Pantheon-RP-1.6-12b-Nemo-Q2_K.gguf | Q2_K | 4.79GB | ❌ | Very low quality but surprisingly usable. |
| Pantheon-RP-1.6-12b-Nemo-IQ2_M.gguf | IQ2_M | 4.44GB | ❌ | Relatively low quality, uses SOTA techniques to be surprisingly usable. |