Mixtral 8x7B V0.1 GPTQ is an open-source language model by TheBloke. Features: 46.7b LLM, VRAM: 23.8GB, Context: 32K, License: apache-2.0, MoE, Quantized, LLM Explorer Score: 0.12, Arc: 65.2, HellaSwag: 84.7, MMLU: 69.4, GSM8K: 48.3.
Mixtral 8x7B V0.1 GPTQ Parameters and Internals
| Model Type | |
| Use Cases |
| Areas: | | research, commercial applications |
|
| Limitations: | | No moderation mechanisms as it's a pre-trained base model |
|
|
| Supported Languages | | fr (fluent), it (fluent), de (fluent), es (fluent), en (fluent) |
|
| Training Details |
| Data Sources: | | VMware Open Instruct for quantization |
|
| Context Length: | |
| Model Architecture: | | Sparse Mixture of Experts |
|
|
| Input Output |
| Input Format: | |
| Accepted Modalities: | |
| Output Format: | |
|
| LLM Name | Mixtral 8x7B V0.1 GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GPTQ |
| Model Name | Mixtral 8X7B v0.1 |
| Model Creator | Mistral AI_ |
| Base Model(s) | mistralai/Mixtral-8x7B-v0.1 mistralai/Mixtral-8x7B-v0.1 |
| Model Size | 46.7b |
| Required VRAM | 23.8 GB |
| Updated | 2026-06-06 |
| Maintainer | TheBloke |
| Model Type | mixtral |
| Model Files | 23.8 GB |
| Supported Languages | fr it de es en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Mixtral 8x7B V0.1 GPTQ