Downloads · 30 days
155
18% of all-time downloads
FahadPrimeX-b27
FahadPrimeX/FahadPrimeX-b27
FahadPrimeX-b27 is a text generation model from FahadPrimeX. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
The original 27B BF16 release: Qwen3.8-27B distilled on 5,181 verified Three.js/HTML/CSS/JS answers.
All-time downloads
859
Public
Parameters
26.9B
53.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors53.8 GB · 100%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Model type
- qwen3_5_text
- Access
- Public
- Created
- Sep 19, 2026
- Updated
- Sep 21, 2026
- SHA
- c4407425
Model card
From the Hugging Face model README
FahadPrimeX-b27 ⭐ (original)
The original 27B BF16 release: Qwen3.8-27B distilled on 5,181 verified Three.js/HTML/CSS/JS answers.
Architecture (inherited from Qwen3.8-27B)
A hybrid 64-layer design: 48 linear-attention layers (DeltaNet-style, constant-memory recurrence) interleaved with 16 full-attention layers (every 4th layer), plus one MTP/nextn draft layer used only by the original spec (excluded from our GGUF exports via --no-nextn so block_count matches the real 64 blocks).
Quick start
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"FahadPrimeX/FahadPrimeX-b27", torch_dtype="bfloat16", device_map="auto")
tok = AutoTokenizer.from_pretrained("FahadPrimeX/FahadPrimeX-b27")
Tip for best game output: start the assistant turn with an HTML prefill (<!DOCTYPE html>) — the model continues full Three.js pages reliably.
- Task
- Text Generation
- Type
- qwen3_5_text
- License
- apache-2.0
- Languages
- ar, en, zh
- Created
- Sep 19, 2026
- Updated
- Sep 21, 2026