Merges
Collection
17 items
•
Updated
•
1
Llamacpp Quantizations of knifeayumu/Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP
Using llama.cpp release b3787 for quantization.
Original model: knifeayumu/Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP
Quant Types:
| Filename | Quant type | File Size |
|---|---|---|
| Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-F16.gguf | F16 | 24.5GB |
| Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-Q8_0.gguf | Q8_0 | 13GB |
| Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-Q6_K.gguf | Q6_K | 10.1GB |
| Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-Q5_K_M.gguf | Q5_K_M | 8.73GB |
| Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-Q5_K_S.gguf | Q5_K_S | 8.52GB |
| Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-Q4_K_M.gguf | Q4_K_M | 7.48GB |
| Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-Q4_K_S.gguf | Q4_K_S | 7.12GB |
| Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-Q3_K_L.gguf | Q3_K_L | 6.56B |
| Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-Q3_K_M.gguf | Q3_K_M | 6.08GB |
| Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-Q3_K_S.gguf | Q3_K_S | 5.53GB |
| Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-Q2_K.gguf | Q2_K | 4.79GB |
- Downloads last month
- 991
Hardware compatibility
Log In
to view the estimation
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
16-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.