4-bit Autotrain compatible Bitsandbytes Dataset:jondurbin/airoboros-3.... En Exl2 Lora Mixtral Moe Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/Air-Striker-Mixtral-8x7B-ZLoss-3.75bpw-h6-exl2
Air Striker Mixtral 8x7B ZLoss 3.75bpw H6 EXL2 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)
Air Striker Mixtral 8x7B ZLoss 3.75bpw H6 EXL2 Parameters and Internals
| Additional Notes |
| |||||||||
| Training Details |
|
| LLM Name | Air Striker Mixtral 8x7B ZLoss 3.75bpw H6 EXL2 |
| Repository 🤗 | https://huggingface.co/LoneStriker/Air-Striker-Mixtral-8x7B-ZLoss-3.75bpw-h6-exl2 |
| Required VRAM | 22.2 GB |
| Updated | 2025-09-23 |
| Maintainer | LoneStriker |
| Model Files | |
| Supported Languages | en |
| Quantization Type | exl2 |
| Model Architecture | AutoModelForCausalLM |
| License | apache-2.0 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|w1|v_proj|gate|o_proj|w3|k_proj|w2 |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.07 |
| R Param | 64 |
Best Alternatives to Air Striker Mixtral 8x7B ZLoss 3.75bpw H6 EXL2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mistral | 0K / 0.2 GB | 5 | 0 |
| ...emo Instruct 2407 EXL2 8bpw H8 | 0K / 12.6 GB | 13 | 7 |
| Dre Phi | 0K / 7.6 GB | 7 | 0 |
| Phi 3 Mini 4K CodeInstruct | 0K / 7.6 GB | 5 | 0 |
| ...3 Mini 4K Instruct Text To Sql | 0K / 7.6 GB | 16 | 0 |
| Asdf | 0K / 0.1 GB | 14 | 0 |
| MS32 3 | 0K / 1.5 GB | 6 | 0 |
| MS32 2 | 0K / 0.7 GB | 5 | 0 |
| Phi 3 Mini 4K Python | 0K / 7.6 GB | 138 | 1 |
| Tinyllama Cpt | 0K / 0.5 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Air-Striker-Mixtral-8x7B-ZLoss-3.75bpw-h6-exl2 .
Rank the Air Striker Mixtral 8x7B ZLoss 3.75bpw H6 EXL2 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? 51597 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124