Downloads · 30 days
181
3% of all-time downloads
RichardErkhov/xxx777xxxASD_-_L3.1-ClaudeMaid-4x8B-gguf
xxx777xxxASD_-_L3.1-ClaudeMaid-4x8B-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
181
3% of all-time downloads
All-time downloads
6.7K
Public
Repo size
283 GB
Likes
1
Public
Click a slice to open those files.
.gguf328 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
L3.1-ClaudeMaid-4x8B - GGUF
| Name | Quant method | Size |
|---|---|---|
| L3.1-ClaudeMaid-4x8B.Q2_K.gguf | Q2_K | 8.66GB |
| L3.1-ClaudeMaid-4x8B.IQ3_XS.gguf | IQ3_XS | 9.68GB |
| L3.1-ClaudeMaid-4x8B.IQ3_S.gguf | IQ3_S | 10.2GB |
| L3.1-ClaudeMaid-4x8B.Q3_K_S.gguf | Q3_K_S | 10.18GB |
| L3.1-ClaudeMaid-4x8B.IQ3_M.gguf | IQ3_M | 10.38GB |
| L3.1-ClaudeMaid-4x8B.Q3_K.gguf | Q3_K | 11.25GB |
| L3.1-ClaudeMaid-4x8B.Q3_K_M.gguf | Q3_K_M | 11.25GB |
| L3.1-ClaudeMaid-4x8B.Q3_K_L.gguf | Q3_K_L | 12.15GB |
| L3.1-ClaudeMaid-4x8B.IQ4_XS.gguf | IQ4_XS | 12.65GB |
| L3.1-ClaudeMaid-4x8B.Q4_0.gguf | Q4_0 | 13.2GB |
| L3.1-ClaudeMaid-4x8B.IQ4_NL.gguf | IQ4_NL | 13.33GB |
| L3.1-ClaudeMaid-4x8B.Q4_K_S.gguf | Q4_K_S | 13.31GB |
| L3.1-ClaudeMaid-4x8B.Q4_K.gguf | Q4_K | 14.12GB |
| L3.1-ClaudeMaid-4x8B.Q4_K_M.gguf | Q4_K_M | 14.12GB |
| L3.1-ClaudeMaid-4x8B.Q4_1.gguf | Q4_1 | 14.62GB |
| L3.1-ClaudeMaid-4x8B.Q5_0.gguf | Q5_0 | 16.04GB |
| L3.1-ClaudeMaid-4x8B.Q5_K_S.gguf | Q5_K_S | 16.04GB |
| L3.1-ClaudeMaid-4x8B.Q5_K.gguf | Q5_K | 16.52GB |
| L3.1-ClaudeMaid-4x8B.Q5_K_M.gguf | Q5_K_M | 16.52GB |
| L3.1-ClaudeMaid-4x8B.Q5_1.gguf | Q5_1 | 17.47GB |
| L3.1-ClaudeMaid-4x8B.Q6_K.gguf | Q6_K | 19.06GB |
| L3.1-ClaudeMaid-4x8B.Q8_0.gguf | Q8_0 | 24.69GB |
language:
[!WARNING] GGUF
Experimental RP-oriented MoE
base_model: NeverSleep_Lumimaid-v0.2-8B
gate_mode: random
dtype: bfloat16
experts_per_token: 2
experts:
- source_model: aifeifei798_DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored
- source_model: Nitral-AI_Sekhmet_Bet-L3.1-8B-v0.2
- source_model: NeverSleep_Lumimaid-v0.2-8B
- source_model: Undi95_Meta-Llama-3.1-8B-Claude-bf16
It seems like 1.71 koboldcpp can't run GGUFs of llama-3.1 MoE models yet, or perhaps im just dumb and messed something up.
If anyone has similar problem - run the model directly from llama.cpp, here's simple open source GUI(Windows) you can use if the console is your worst enemy

UPDATE 28.07.2024 Try this koboldcpp version