Model Type |
| |
Additional Notes |
|
LLM Name | Tenebra 30B Alpha01 3BIT |
Repository π€ | https://huggingface.co/SicariusSicariiStuff/Tenebra_30B_Alpha01_3BIT |
Model Size | 30b |
Required VRAM | 12.9 GB |
Updated | 2025-02-22 |
Maintainer | SicariusSicariiStuff |
Model Type | llama |
Model Files | |
Supported Languages | en |
Quantization Type | 3bit |
Model Architecture | LlamaForCausalLM |
License | apache-2.0 |
Context Length | 16384 |
Model Max Length | 16384 |
Transformers Version | 4.36.0 |
Vocabulary Size | 32000 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Tenebra 30B Alpha01 FP16 | 16K / 65 GB | 1792 | 8 |
Tenebra 30B Alpha01 4BIT | 16K / 19.4 GB | 1896 | 1 |
...nebra 30B Alpha01 EXL2 2 80bpw | 16K / 11.9 GB | 12 | 1 |
Tenebra 30B Alpha01 EXL2 3bpw | 16K / 12.7 GB | 11 | 0 |
...nebra 30B Alpha01 EXL2 2 50bpw | 16K / 10.7 GB | 6 | 0 |
... 30B Supercot SuperHOT 8K Fp16 | 8K / 65.2 GB | 2072 | 4 |
Platypus 30B SuperHOT 8K Fp16 | 8K / 65.2 GB | 2071 | 2 |
GPlatty 30B SuperHOT 8K Fp16 | 8K / 65.2 GB | 2061 | 1 |
Tulu 30B Fp16 | 2K / 65.2 GB | 2057 | 5 |
WizardLM 30B Fp16 | 2K / 65.2 GB | 2058 | 10 |
π Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! π