lzlv longLORA 70b rope8 32k - GGUF
- Model creator: Grimulkan
- Original model: lzlv longLORA 70b rope8 32k
Description
This repo contains GGUF format model files for Grimulkan's lzlv longLORA 70b rope8 32k.
Provided files
| Name | Quant method | Bits | Size |
|---|---|---|---|
| lzlv-longLORA-70b-rope8-32k.Q2_K.gguf | Q2_K | 2 | 25.46 GB |
| lzlv-longLORA-70b-rope8-32k.Q3_K_M.gguf | Q3_K_M | 3 | 33.27 GB |
| lzlv-longLORA-70b-rope8-32k.Q4_K_S.gguf | Q4_K_S | 4 | 39.25 GB |
| lzlv-longLORA-70b-rope8-32k.Q4_K_M.gguf | Q4_K_M | 4 | 41.42 GB |
| lzlv-longLORA-70b-rope8-32k.Q5_K_S.gguf | Q5_K_S | 5 | 47.46 GB |
| lzlv-longLORA-70b-rope8-32k.Q5_K_M.gguf | Q5_K_M | 5 | 48.75 GB |
| lzlv-longLORA-70b-rope8-32k.Q6_K.gguf | Q6_K | 6 | 56.59 GB |
| lzlv-longLORA-70b-rope8-32k.Q8_0.gguf | Q8_0 | 8 | 73.29 GB |
Note: HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.
- Downloads last month
- 159
Inference API (serverless) has been turned off for this model.