Interfaze

logo

Beta

pricing

help

docs

blog

sign in

Fable Traces

Fable Traces by AliesTaha, a text-generation model. Understand and compare features, benchmarks, and capabilities.

Comparison

FeatureFable TracesInterfaze
Input Modalities

text

image, text, audio, video, document

Native OCRNoYes
Long Document ProcessingNoYes
Language Support

unknown

162+

Native Speech-to-TextNoYes
Native Object DetectionNoYes
Guardrail ControlsNoYes
Context Input Size

32.8K

1M

Tool CallingNo

Tool calling supported + built in browser, code execution and web search

Scaling

FeatureFable TracesInterfaze
Scaling

Self-hosted/Provider-hosted with quantization

Unlimited

View model card on Hugging Face

A compact instruction-tuned language model built on Qwen/Qwen3-4B-Instruct-2507. fable-traces is tuned for short, conversational replies and runs comfortably on a single mid-range GPU.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "AliesTaha/fable-traces"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, dtype=torch.bfloat16, device_map="auto")

messages = [{"role": "user", "content": "Tell me something interesting."}]
ids = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(ids, max_new_tokens=100, do_sample=False)
print(tok.decode(out[0, ids.shape[1]:], skip_special_tokens=True))

Serve with vLLM:

vllm serve AliesTaha/fable-traces

Details

Base modelQwen3-4B-Instruct-2507
Parameters~4B
Precisionbfloat16 (safetensors)
Prompt formatChatML — use the tokenizer's chat template
Context lengthinherits the base model

License

Apache 2.0, following the base model.

This is a joke. This is not an actual model. Please read the full post first

Want more deterministic results?