Fixed 3.1 GGUFs require KoboldCPP 1.17.1 or newer to run.

Models Q2_K_L, Q4_K_L, Q5_K_L, Q6_K_L, are using Q_8 output tensors and token embeddings

using bartowski's imatrix dataset

GGUF

Model size

24.9B params

Architecture

llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples

Inference API (serverless) is not available, repository is disabled.

Model tree for Reiterate3680/L3.1-ClaudeMaid-4x8B-GGUF

Base model

Quantized

this model