Views
No views yet
Powered by Featherless AI - run any model you'd like for a simple small fee.
| Quantization Type | File | Size |
|---|---|---|
| IQ4_XS | wang7776-Mistral-7B-Instruct-v0.2-attention-sparsity-20-IQ4_XS.gguf | 3761.66 MB |
| Q2_K | wang7776-Mistral-7B-Instruct-v0.2-attention-sparsity-20-Q2_K.gguf | 2593.27 MB |
| Q3_K_L | wang7776-Mistral-7B-Instruct-v0.2-attention-sparsity-20-Q3_K_L.gguf | 3644.97 MB |
| Q3_K_M | wang7776-Mistral-7B-Instruct-v0.2-attention-sparsity-20-Q3_K_M.gguf | 3355.97 MB |
| Q3_K_S | wang7776-Mistral-7B-Instruct-v0.2-attention-sparsity-20-Q3_K_S.gguf | 3017.97 MB |
| Q4_K_M | wang7776-Mistral-7B-Instruct-v0.2-attention-sparsity-20-Q4_K_M.gguf | 4166.07 MB |
| Q4_K_S | wang7776-Mistral-7B-Instruct-v0.2-attention-sparsity-20-Q4_K_S.gguf | 3948.57 MB |
| Q5_K_M | wang7776-Mistral-7B-Instruct-v0.2-attention-sparsity-20-Q5_K_M.gguf | 4893.69 MB |
| Q5_K_S | wang7776-Mistral-7B-Instruct-v0.2-attention-sparsity-20-Q5_K_S.gguf | 4766.19 MB |
| Q6_K | wang7776-Mistral-7B-Instruct-v0.2-attention-sparsity-20-Q6_K.gguf | 5666.80 MB |
| Q8_0 | wang7776-Mistral-7B-Instruct-v0.2-attention-sparsity-20-Q8_0.gguf | 7339.34 MB |