Arxiv:1910.09700 4-bit 4bit Autotrain compatible Bitsandbytes Endpoints compatible Mixtral Moe Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/monsterapi/Mixtral-8x7B-v0.1_4bit_bnb
Mixtral 8x7B V0.1 4bit Bnb 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 8x7B V0.1 4bit Bnb Parameters and Internals
| LLM Name | Mixtral 8x7B V0.1 4bit Bnb |
| Repository 🤗 | https://huggingface.co/monsterapi/Mixtral-8x7B-v0.1_4bit_bnb |
| Model Size | 24.2b |
| Required VRAM | 24.5 GB |
| Updated | 2025-02-22 |
| Maintainer | monsterapi |
| Model Type | mixtral |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | MixtralForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Mixtral 8x7B V0.1 4bit Bnb
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...al 8x7B Instruct V0.1 4bit Bnb | 32K / 24.5 GB | 8 | 1 |
| ...ixtral 8x7B Instruct V0.1 4bit | 32K / 24.5 GB | 54 | 2 |
| ...al 8x7B Instruct V0.1 Bnb 4bit | 32K / 26.7 GB | 196 | 59 |
| Dzakwan MoE 4x7b Beta | 32K / 48.4 GB | 3844 | 0 |
| Beyonder 4x7B V3 | 32K / 48.3 GB | 3941 | 58 |
| Calme 4x7B MoE V0.2 | 32K / 48.3 GB | 5636 | 2 |
| Proto Athena 4x7B | 32K / 48.4 GB | 15 | 0 |
| Proto Athena V0.2 4x7B | 32K / 48.4 GB | 8 | 0 |
| Mera Mix 4x7B | 32K / 48.3 GB | 3525 | 18 |
| Calme 4x7B MoE V0.1 | 32K / 48.3 GB | 3951 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than monsterapi/Mixtral-8x7B-v0.1_4bit_bnb .
Rank the Mixtral 8x7B V0.1 4bit Bnb 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227