Sonya Medium X8 MoE GPTQ is an open-source language model by TheBloke. Features: 69.9b LLM, VRAM: 35.5GB, Context: 8K, License: wtfpl, MoE, Quantized, LLM Explorer Score: 0.11.
Model Card on HF 🤗: https://huggingface.co/TheBloke/sonya-medium-x8-MoE-GPTQ
Sonya Medium X8 MoE GPTQ 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)
Sonya Medium X8 MoE GPTQ Parameters and Internals
| Model Type |
|
| LLM Name | Sonya Medium X8 MoE GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/sonya-medium-x8-MoE-GPTQ |
| Model Name | Sonya Medium x8 MoE |
| Model Creator | Cross Nastasi |
| Base Model(s) | |
| Model Size | 69.9b |
| Required VRAM | 35.5 GB |
| Updated | 2026-02-13 |
| Maintainer | TheBloke |
| Model Type | mixtral |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | MixtralForCausalLM |
| License | wtfpl |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Sonya Medium X8 MoE GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...urningBruce SOLAR 8x10.7B Bf16 | 4K / 140 GB | 640 | 4 |
| Seraphim 8x10.7B Bf16 | 4K / 140 GB | 687 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/sonya-medium-x8-MoE-GPTQ .
Rank the Sonya Medium X8 MoE GPTQ 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? 52473 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 v20260328a