LLM Name | Meta Llama 3.1 405B 2bit |
Repository ๐ค | https://huggingface.co/mlx-community/Meta-Llama-3.1-405B-2bit |
Model Size | 405b |
Required VRAM | 128 GB |
Updated | 2025-09-08 |
Maintainer | mlx-community |
Model Type | llama |
Model Files | |
Supported Languages | en de fr it pt hi es th |
Quantization Type | 2bit |
Model Architecture | LlamaForCausalLM |
License | meta |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.42.3 |
Tokenizer Class | PreTrainedTokenizerFast |
Vocabulary Size | 128256 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Meta Llama 3.1 405B Bnb 4bit | 128K / 214.3 GB | 1170 | 17 |
Meta Llama 3.1 405B 4bit | 128K / 231.9 GB | 1181 | 5 |
...ama 3.1 405B Instruct Bnb 4bit | 128K / 214.3 GB | 239 | 6 |
Hermes 4 405B FP8 | 128K / 213.8 GB | 2347 | 16 |
AGI 405B | 128K / 191.2 GB | 511 | 3 |
Hermes 4 405B | 128K / 191.2 GB | 403 | 54 |
Hermes 4 405B GGUF | 128K / GB | 2261 | 2 |
Meta Llama 3.1 405B | 128K / 186 GB | 521433 | 808 |
Cogito V2 Preview Llama 405B | 128K / 189.7 GB | 1292 | 10 |
Meta Llama 3.1 405B Instruct | 128K / 186 GB | 55654 | 473 |
๐ 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! ๐