Downloads · 30 days
84
3% of all-time downloads
RichardErkhov/upvantage_-_llama32-gptcleaned-30k-gguf
upvantage_-_llama32-gptcleaned-30k-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
84
3% of all-time downloads
All-time downloads
2.5K
Public
Repo size
38.1 GB
Likes
0
Public
Click a slice to open those files.
.gguf44.2 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
llama32-gptcleaned-30k - GGUF
| Name | Quant method | Size |
|---|---|---|
| llama32-gptcleaned-30k.Q2_K.gguf | Q2_K | 1.27GB |
| llama32-gptcleaned-30k.IQ3_XS.gguf | IQ3_XS | 1.38GB |
| llama32-gptcleaned-30k.IQ3_S.gguf | IQ3_S | 1.44GB |
| llama32-gptcleaned-30k.Q3_K_S.gguf | Q3_K_S | 1.44GB |
| llama32-gptcleaned-30k.IQ3_M.gguf | IQ3_M | 1.49GB |
| llama32-gptcleaned-30k.Q3_K.gguf | Q3_K | 1.57GB |
| llama32-gptcleaned-30k.Q3_K_M.gguf | Q3_K_M | 1.57GB |
| llama32-gptcleaned-30k.Q3_K_L.gguf | Q3_K_L | 1.69GB |
| llama32-gptcleaned-30k.IQ4_XS.gguf | IQ4_XS | 1.71GB |
| llama32-gptcleaned-30k.Q4_0.gguf | Q4_0 | 1.79GB |
| llama32-gptcleaned-30k.IQ4_NL.gguf | IQ4_NL | 1.79GB |
| llama32-gptcleaned-30k.Q4_K_S.gguf | Q4_K_S | 1.8GB |
| llama32-gptcleaned-30k.Q4_K.gguf | Q4_K | 1.88GB |
| llama32-gptcleaned-30k.Q4_K_M.gguf | Q4_K_M | 1.88GB |
| llama32-gptcleaned-30k.Q4_1.gguf | Q4_1 | 1.95GB |
| llama32-gptcleaned-30k.Q5_0.gguf | Q5_0 | 2.11GB |
| llama32-gptcleaned-30k.Q5_K_S.gguf | Q5_K_S | 2.11GB |
| llama32-gptcleaned-30k.Q5_K.gguf | Q5_K | 2.16GB |
| llama32-gptcleaned-30k.Q5_K_M.gguf | Q5_K_M | 2.16GB |
| llama32-gptcleaned-30k.Q5_1.gguf | Q5_1 | 2.28GB |
| llama32-gptcleaned-30k.Q6_K.gguf | Q6_K | 2.46GB |
| llama32-gptcleaned-30k.Q8_0.gguf | Q8_0 | 3.19GB |
base_model: unsloth/Llama-3.2-3B language:
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.