LLM Name | Normistral 11B Warm |
Repository ๐ค | https://huggingface.co/norallm/normistral-11b-warm |
Base Model(s) | |
Model Size | 11b |
Required VRAM | 22.9 GB |
Updated | 2025-06-09 |
Maintainer | norallm |
Model Type | mistral |
Model Files | |
Supported Languages | nb nn no se sv da en is fo |
GGUF Quantization | Yes |
Quantization Type | gguf |
Model Architecture | MistralForCausalLM |
License | apache-2.0 |
Context Length | 1024000 |
Model Max Length | 1024000 |
Transformers Version | 4.44.0.dev0 |
Tokenizer Class | PreTrainedTokenizerFast |
Vocabulary Size | 51200 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Huginn V5.10.7B | 32K / 21.4 GB | 0 | 0 |
... 11B V2.2 Instruct EXL2 4.5bit | 32K / 6.5 GB | 44 | 3 |
...B V2.2 Instruct HQQ 4bit 128gs | 32K / 6.2 GB | 24 | 3 |
...B V2.2 Instruct HQQ 8bit 128gs | 32K / 11.7 GB | 19 | 3 |
...t 3.1 Frankenmerge 11B Gguf Q8 | 32K / 8.3 GB | 28 | 1 |
Bielik 11B V2.2 Instruct GPTQ | 32K / 6.2 GB | 141 | 3 |
... 11B V2.2 Instruct Quanto 8bit | 32K / 12 GB | 45 | 4 |
Bielik 11B V2.2 Instruct FP8 | 32K / 11.4 GB | 39 | 3 |
Bielik 11B V2.2 Instruct W8A8 | 32K / 11.5 GB | 31 | 3 |
Bielik 11B V2.2 Instruct AWQ | 32K / 6.2 GB | 23 | 3 |
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