4-bit Autotrain compatible Bitsandbytes Conversational Endpoints compatible Instruct Mixtral Moe Region:us Safetensors Sharded Tensorflow
Mistralai Mixtral 8x7B Instruct V0.1 4bits 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)
Mistralai Mixtral 8x7B Instruct V0.1 4bits Parameters and Internals
| LLM Name | Mistralai Mixtral 8x7B Instruct V0.1 4bits |
| Repository 🤗 | https://huggingface.co/RichardErkhov/mistralai_-_Mixtral-8x7B-Instruct-v0.1-4bits |
| Model Size | 24.2b |
| Required VRAM | 26.7 GB |
| Updated | 2024-09-18 |
| Maintainer | RichardErkhov |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | fr it de es en |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.39.3 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Mistralai Mixtral 8x7B Instruct V0.1 4bits
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| WizardLM 2 8x22B Beige | 64K / 221.4 GB | 3 | 3 |
| Dolphin 2.7 Mixtral 8x7b | 32K / 93.6 GB | 5042 | 155 |
| Dolphin 2.6 Mixtral 8x7b | 32K / 93.6 GB | 5110 | 187 |
| ...eqlen 4096 Bs 4 Optimum 0 0 23 | 32K / GB | 186 | 0 |
| ...eqlen 4096 Bs 4 Optimum 0 0 23 | 32K / GB | 3 | 1 |
| Empower Functions Medium | 32K / 93.6 GB | 9 | 1 |
| Mixtral 8x7B Instruct V0.1 | 32K / GB | 13 | 0 |
| ...ral 8x7b Instruct V0.1 Int4 Ov | 32K / 0 GB | 31 | 3 |
| ...ct V0.1 Agent Function Calling | 32K / 44.3 GB | 6 | 2 |
| ...tral 8x7B Instruct V0.1 Polish | 32K / 93.6 GB | 5 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than RichardErkhov/mistralai_-_Mixtral-8x7B-Instruct-v0.1-4bits .
Rank the Mistralai Mixtral 8x7B Instruct V0.1 4bits 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? 36026 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803