GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

ilintar/Ornith-1.0-35B-GGUF overview

Optimized with my branch's custom auto tensor type , custom made recipes for 2.91, 3.74 and 4.34 bpw element gamma=0.25, which beats the stock hand tuned recip…

ggufbase_model:deepreinforce-ai/Ornith-1.0-35Bbase_model:quantized:deepreinforce-ai/Ornith-1.0-35Blicense:mitendpoints_compatibleregion:usimatrixconversational

Runs locally from ~11.82 GB disk (12 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
848
Likes
0
Pipeline
Author

Repository Files & Downloads

3 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Ornith-1.0-35B-IQ3_M.ggufGGUFIQ3_M15.18 GBDownload
Ornith-1.0-35B-IQ4_XS.ggufGGUFIQ4_XS17.58 GBDownload
Ornith-1.0-35B-Q2_K.ggufGGUFQ2_K11.82 GBDownload

Model Details

Model IDilintar/Ornith-1.0-35B-GGUF
Authorilintar
Pipeline
Licensemit
Base modeldeepreinforce-ai/Ornith-1.0-35B
Last modified2026-07-09T13:14:41.000Z

Model README

---

license: mit

base_model:

  • deepreinforce-ai/Ornith-1.0-35B

---

Optimized with my branch's custom auto-tensor-type, custom-made recipes for 2.91, 3.74 and 4.34 bpw

(element-gamma=0.25, which beats the stock hand-tuned recipes at matched BPW).

Since HF doesn't recognize custom bpw tags, I've tagged them with:

  • Q2_K: 2.91bpw
  • IQ3_M: 3.74bpw
  • IQ4_XS: 4.34bpw

Note that the quant types are only aliases for the size and do not correspond to the actual quant types used.

Run ilintar/Ornith-1.0-35B-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models