Midas FableAgent 8B is an open-source language model by EphAsad. Features: 8b LLM, VRAM: 16.4GB, Context: 40K, License: apache-2.0, Quantized, LLM Explorer Score: 0.27.
Agentic Base model:adapter:ephasad/ate... Base model:ephasad/atem-8b Conversational Dataset:armand0e/claude-fable-... Dataset:glint-research/fable-5... Dataset:kelexine/fable-5-sft-t... Dataset:open-thoughts/openthou... En Endpoints compatible Gguf Lora Quantized Qwen3 Reasoning Region:us Safetensors Sharded Tensorflow Tool-use Unsloth
Model Card on HF 🤗: https://huggingface.co/EphAsad/Midas-FableAgent-8B
Midas FableAgent 8B 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)
Midas FableAgent 8B Parameters and Internals
| LLM Name | Midas FableAgent 8B |
| Repository 🤗 | https://huggingface.co/EphAsad/Midas-FableAgent-8B |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 16.4 GB |
| Updated | 2026-06-30 |
| Maintainer | EphAsad |
| Model Type | qwen3 |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | gguf |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|PAD_TOKEN|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Midas FableAgent 8B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| DeepSeek R1 0528 Qwen3 8B GGUF | 128K / 2.3 GB | 49632 | 398 |
| Qwen3 8B 128K GGUF | 128K / 2.3 GB | 3466 | 26 |
| Qwen3 8B GGUF | 40K / 2.3 GB | 46817 | 107 |
| CustomThinker 0 8B | 40K / 16.4 GB | 169 | 29 |
| BehChat SFTv2 Mixed Ckpt 6 | 128K / 16.4 GB | 131 | 0 |
| BehChat SFTv3 Ckpt1 | 128K / 16.4 GB | 42 | 0 |
| ...0528 Qwen3 8B Unsloth Bnb 4bit | 128K / 7.5 GB | 7204 | 13 |
| DeepSeek R1 0528 Qwen3 8B 4bit | 128K / 4.6 GB | 1860 | 5 |
| ...Seek R1 0528 Qwen3 8B Bnb 4bit | 128K / 6.1 GB | 560 | 10 |
| Qwen3 8B LQA 14e Full | 128K / 16.4 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than EphAsad/Midas-FableAgent-8B .
Rank the Midas FableAgent 8B 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? 54677 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