LLM EXPLORER 59,358 MODELS INDEXED

Openbuddy Mistral 10B V17.1 32K 8.0bpw H8 EXL2 by LoneStriker

By LoneStriker · 3 downloads

Openbuddy Mistral 10B V17.1 32K 8.0bpw H8 EXL2 is an open-source language model by LoneStriker. Features: 10b LLM, VRAM: 10.9GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.11.

  Endpoints compatible   Exl2   Mistral   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Openbuddy Mistral 10B V17.1 32K 8.0bpw H8 EXL2 Parameters and Internals

LLM NameOpenbuddy Mistral 10B V17.1 32K 8.0bpw H8 EXL2
Repository πŸ€—https://huggingface.co/LoneStriker/openbuddy-mistral-10b-v17.1-32k-8.0bpw-h8-exl2 
Model Size10b
Required VRAM10.9 GB
Updated2026-07-22
MaintainerLoneStriker
Model Typemistral
Model Files  8.6 GB: 1-of-2   2.3 GB: 2-of-2
Quantization Typeexl2
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size36608
Torch Data Typebfloat16

Best Alternatives to Openbuddy Mistral 10B V17.1 32K 8.0bpw H8 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
Contrail 200M 64K64K / 0.4 GB82
Contrail 200M 64K64K / 0.4 GB00
NarutoDolphin 10B32K / 21.5 GB482
Occiglot10b DPO32K / 19.7 GB41
Sirius 10B32K / 21.5 GB731
Mistral Passthrough 8L 10B32K / 14.5 GB540
...penbuddy Mistral 10B V17.1 32K32K / 21.5 GB65
Voldemort 10B DPO8K / 21.4 GB910
Voldemort 10B8K / 21.5 GB590
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/openbuddy-mistral-10b-v17.1-32k-8.0bpw-h8-exl2.