Mixtral 8x22B V0.1 Bnb 4bit Smashed is an open-source language model by PrunaAI. Features: 72.7b LLM, VRAM: 80.2GB, Context: 64K, MoE, Quantized, LLM Explorer Score: 0.13.
Model Card on HF 🤗: https://huggingface.co/PrunaAI/Mixtral-8x22B-v0.1-bnb-4bit-smashed
Mixtral 8x22B V0.1 Bnb 4bit Smashed Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Mixtral 8x22B V0.1 Bnb 4bit Smashed Parameters and Internals
| Model Type |
| |||||||||
| Use Cases |
| |||||||||
| Additional Notes |
| |||||||||
| Training Details |
| |||||||||
| Input Output |
| |||||||||
| Release Notes |
|
| LLM Name | Mixtral 8x22B V0.1 Bnb 4bit Smashed |
| Repository 🤗 | https://huggingface.co/PrunaAI/Mixtral-8x22B-v0.1-bnb-4bit-smashed |
| Model Size | 72.7b |
| Required VRAM | 80.2 GB |
| Updated | 2025-09-28 |
| Maintainer | PrunaAI |
| Model Type | mixtral |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | MixtralForCausalLM |
| Context Length | 65536 |
| Model Max Length | 65536 |
| Transformers Version | 4.40.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Rank the Mixtral 8x22B V0.1 Bnb 4bit Smashed Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a