| LLM Name | Miqu 1 70B 24GB VRAM IQ2 XS SOTA |
| Repository ๐ค | https://huggingface.co/amthe/Miqu-1-70b-24GB-VRAM-IQ2-XS-SOTA |
| Model Size | 70b |
| Required VRAM | 20.3 GB |
| Updated | 2025-09-23 |
| Maintainer | amthe |
| Model Type | llama |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | gguf |
| Model Architecture | LlamaForCausalLM |
| Context Length | 32764 |
| Model Max Length | 32764 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...Seek R1 Distill Llama 70B GGUF | 128K / 15.9 GB | 12553 | 91 |
| Llama 3.3 70B Instruct GGUF | 128K / 15.9 GB | 11371 | 82 |
| R1 1776 Distill Llama 70B GGUF | 128K / 26.4 GB | 568 | 22 |
| Reflection Llama 3.1 70B Bf16 | 128K / 141.9 GB | 283 | 6 |
| Reflection Llama 3.1 70B GGUF | 128K / 26.4 GB | 68 | 6 |
| ...Horizon AI Korean Advanced 70B | 128K / 141.9 GB | 26 | 0 |
| Midnight Miqu 70B V1.0 GGUF | 31K / 29.9 GB | 1297 | 4 |
| ...ma3 70B Chinese Chat GGUF 4bit | 8K / 40 GB | 545 | 18 |
| Llama 3 70B Quantised | 8K / 48.7 GB | 32 | 2 |
| ...3 Mega Dolphin 2.9.1 120b GGUF | 8K / 18.4 GB | 30 | 1 |
๐ 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! ๐