Mixtral 8x7B Instruct V0.1 AQLM 2Bit 1x16 Hf is an open-source language model by ISTA-DASLab. Features: 6.5b LLM, VRAM: 13.1GB, Context: 32K, MoE, Quantized, Instruction-Based, LLM Explorer Score: 0.13.
Arxiv:2401.06118 2bit Aqlm Autotrain compatible Conversational Endpoints compatible Instruct Mixtral Moe Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf
Mixtral 8x7B Instruct V0.1 AQLM 2Bit 1x16 Hf 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 Instruct V0.1 AQLM 2Bit 1x16 Hf Parameters and Internals
| Model Type |
| |
| Additional Notes |
|
| LLM Name | Mixtral 8x7B Instruct V0.1 AQLM 2Bit 1x16 Hf |
| Repository 🤗 | https://huggingface.co/ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf |
| Model Size | 6.5b |
| Required VRAM | 13.1 GB |
| Updated | 2025-09-23 |
| Maintainer | ISTA-DASLab |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | 2bit |
| Model Architecture | MixtralForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.38.0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Mixtral 8x7B Instruct V0.1 AQLM 2Bit 1x16 Hf
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mixtral 8x7B Instruct V0.1 AWQ | 32K / 24.7 GB | 11814 | 58 |
| Dolphin 2.7 Mixtral 8x7b AWQ | 32K / 24.7 GB | 7363 | 23 |
| Mixtral 8x7B Instruct V0.1 AWQ | 32K / 24.7 GB | 6 | 0 |
| ...xtral Instruct AWQ Clone Dec23 | 32K / 24.7 GB | 6 | 0 |
| ...0.1 LimaRP ZLoss DARE TIES AWQ | 32K / 24.7 GB | 7 | 3 |
| ...Instruct V0.1 LimaRP ZLoss AWQ | 32K / 24.7 GB | 14 | 1 |
| Dolphin 2.5 Mixtral 8x7b AWQ | 32K / 24.7 GB | 61 | 6 |
| Dolphin 2.6 Mixtral 8x7b AWQ | 32K / 24.7 GB | 9 | 12 |
| ...1 Mixtral 8x7b Instruct V3 AWQ | 32K / 24.7 GB | 6 | 1 |
| ...Mixtral 8x7B V0.1 Dolly15K AWQ | 32K / 24.7 GB | 6 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf .
Rank the Mixtral 8x7B Instruct V0.1 AQLM 2Bit 1x16 Hf 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? 51638 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 v20241124