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: 0.11.
| 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 | 2026-08-06 |
| 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 |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...uct V0.1 OmniQuantv1 W4a16g128 | 32K / 24.7 GB | 12 | 1 |