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

cdanis/Ornith-1.5-397B-GGUF-imatrix overview

Ornith 1.5 397B MTP GGUF vision: yes MTP: yes best quality / byte: yes. pretty sure. bartowski imatrix data Unsloth style mixed quants PPL vs size quality vs s…

llama.cppggufimatrixquantizationmtpbase_model:ornith-ai/Ornith-1.5-397Bbase_model:quantized:ornith-ai/Ornith-1.5-397Bendpoints_compatibleregion:usconversational

Runs locally from ~879.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
15,770
Likes
0
Pipeline
Author

Repository Files & Downloads

12 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Ornith-1.5-397B-IQ1_M-UD.ggufGGUFIQ1_M94.01 GBDownload
Ornith-1.5-397B-IQ1_S-UD.ggufGGUFIQ1_S85.90 GBDownload
Ornith-1.5-397B-IQ2_M-UD.ggufGGUFIQ2_M130.57 GBDownload
Ornith-1.5-397B-IQ2_S-UD.ggufGGUFIQ2_S119.76 GBDownload
Ornith-1.5-397B-IQ2_XXS-UD.ggufGGUFIQ2_XXS107.52 GBDownload
Ornith-1.5-397B-IQ3_S-UD.ggufGGUFIQ3_S168.54 GBDownload
Ornith-1.5-397B-IQ3_XXS-UD.ggufGGUFIQ3_XXS151.54 GBDownload
Ornith-1.5-397B-IQ4_XS-UD.ggufGGUFIQ4_XS209.33 GBDownload
Ornith-1.5-397B-Q3_K_XL-UD.ggufGGUFQ3_K_XL174.30 GBDownload
Ornith-1.5-397B-Q4_K_XL-UD.ggufGGUFQ4_K_XL233.80 GBDownload
imatrix.ggufGGUFGGUF1.06 GBDownload
mmproj-Ornith-1.5-397B-BF16.ggufGGUFBF16879.0 MBDownload

Model Details

Model IDcdanis/Ornith-1.5-397B-GGUF-imatrix
Authorcdanis
Pipeline
License
Base modelornith-ai/Ornith-1.5-397B
Last modified2026-09-08T17:24:06.000Z

Model README

---

base_model:

  • ornith-ai/Ornith-1.5-397B

base_model_relation: quantized

library_name: llama.cpp

tags:

  • gguf
  • imatrix
  • quantization
  • mtp

---

Ornith-1.5-397B MTP GGUF

  • vision: yes
  • MTP: yes!
  • best quality / byte: yes. pretty sure.
  • bartowski imatrix data
  • Unsloth-style mixed quants

!PPL vs size

!Top-token agreement vs size

results.tsv.

Sources

Run cdanis/Ornith-1.5-397B-GGUF-imatrix 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