LLM Name | Magistral Small 2506 Bf16 |
Repository ๐ค | https://huggingface.co/mlx-community/Magistral-Small-2506-bf16 |
Base Model(s) | |
Model Size | 23.6b |
Required VRAM | 46.9 GB |
Updated | 2025-06-14 |
Maintainer | mlx-community |
Model Type | mistral |
Model Files | |
Supported Languages | en fr de es pt it ja ko ru zh ar fa id ms ne pl ro sr sv tr uk vi hi bn |
Model Architecture | MistralForCausalLM |
License | apache-2.0 |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.52.4 |
Tokenizer Class | LlamaTokenizerFast |
Vocabulary Size | 131072 |
Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Magistral Small 2506 4bit DWQ | 4 | 397 | 13 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...stral Small 2501 Tensopolis V1 | 32K / 47.3 GB | 35 | 0 |
XortronCriminalComputingConfig | 32K / 47.3 GB | 644 | 18 |
Sandmisthink24BKaalpac | 32K / 47.3 GB | 32 | 0 |
...stralThinker V1.1 Reasoner 256 | 32K / 47.3 GB | 14 | 0 |
Dans LN | 32K / 47.3 GB | 13 | 1 |
Dans LN 44 | 32K / 47.3 GB | 11 | 0 |
Dans LN 44 | 32K / 47.3 GB | 9 | 0 |
Ms3 Roselily Rp V2 | 32K / 47.3 GB | 16 | 0 |
Aaa2 | 32K / 47.3 GB | 26 | 0 |
Aaa3 | 32K / 47.3 GB | 10 | 0 |
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