Dataset:ewof/koishi-instruct-m... Endpoints compatible Ggml Gguf Instruct Mixtral Moe Q2 Quantized Region:us
Model Card on HF 🤗: https://huggingface.co/ewof/koishi-8x7b-qlora-gguf
Koishi 8x7b Qlora Gguf 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)
Koishi 8x7b Qlora Gguf Parameters and Internals
| Training Details |
| |||||||||
| Input Output |
|
| LLM Name | Koishi 8x7b Qlora Gguf |
| Repository 🤗 | https://huggingface.co/ewof/koishi-8x7b-qlora-gguf |
| Required VRAM | 15.6 GB |
| Updated | 2025-08-23 |
| Maintainer | ewof |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| GGML Quantization | Yes |
| GGUF Quantization | Yes |
| Quantization Type | gguf|ggml|q2|q4_k|q5_k |
| Model Architecture | AutoModel |
Best Alternatives to Koishi 8x7b Qlora Gguf
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...ixtral 8x7B Instruct V0.1 GGUF | 0K / 15.6 GB | 39579 | 636 |
| Dolphin 2.5 Mixtral 8x7b GGUF | 0K / 15.6 GB | 12031 | 303 |
| Dolphin 2.7 Mixtral 8x7b GGUF | 0K / 15.6 GB | 11741 | 145 |
| Phi 3 Mini 4K Instruct GGUF | 0K / 1.4 GB | 1281 | 17 |
| Spydaz Web AI | 0K / 4.4 GB | 154 | 3 |
| Autocomplete Model | 0K / 4.1 GB | 27 | 0 |
| Phi 3 Mini 4K Instruct | 0K / 2.3 GB | 6 | 0 |
| Dre Phi Gguf | 0K / 2.3 GB | 5 | 0 |
| ...i 3 Mini 4K Instruct V0.3 GGUF | 0K / 1.4 GB | 227 | 5 |
| ...3 Mini 4k OLScience 4bitQ Gguf | 0K / 2.3 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ewof/koishi-8x7b-qlora-gguf .
Rank the Koishi 8x7b Qlora Gguf 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? 50836 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124