LLM EXPLORER 59,278 MODELS INDEXED

Midas FableAgent 8B by EphAsad

By EphAsad · 110 downloads
HF Repo ↗ Copy URL

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: 0.26.

  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 Parameters and Internals

LLM NameMidas FableAgent 8B
Repository 🤗https://huggingface.co/EphAsad/Midas-FableAgent-8B 
Base Model(s)  EphAsad/Atem-8B   EphAsad/Atem-8B
Model Size8b
Required VRAM16.4 GB
Updated2026-08-07
MaintainerEphAsad
Model Typeqwen3
Model Files  5.0 GB   5.8 GB   8.7 GB   4.9 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   1.6 GB: 4-of-4
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Midas FableAgent 8B

Best Alternatives
Context / RAM
Downloads
Likes
DeepSeek R1 0528 Qwen3 8B GGUF128K / 2.3 GB52800436
Qwen3 8B 128K GGUF128K / 2.3 GB210628
Qwen3 8B MedReasonPath40K / 16.4 GB3491
Qwen3 8B GGUF40K / 2.3 GB206898140
CustomThinker 0 8B40K / 16.4 GB16329
BehChat SFTv3 Ckpt1128K / 16.4 GB60
BehChat SFTv2 Mixed Ckpt 6128K / 16.4 GB110
...0528 Qwen3 8B Unsloth Bnb 4bit128K / 7.5 GB445713
DeepSeek R1 0528 Qwen3 8B 4bit128K / 4.6 GB17816
...Seek R1 0528 Qwen3 8B Bnb 4bit128K / 6.1 GB9239
Note: green Score (e.g. "73.2") means that the model is better than EphAsad/Midas-FableAgent-8B.