Instructions to use paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF",
	filename="DFlash/Ornith-DFLASH-bf16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16

Use Docker

docker model run hf.co/paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16

LM Studio
Jan
Ollama
How to use paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF with Ollama:
```
ollama run hf.co/paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16
```

Unsloth Studio

How to use paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF to start chatting

How to use paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF with Docker Model Runner:
```
docker model run hf.co/paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16
```

Lemonade

How to use paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF:BF16

Run and chat with the model

lemonade run user.Ornith-1.0-397B-DFLASH-GGUF-BF16

List all available models

lemonade list

Warning, all models only work with ik_llama.cpp

Quants of Ornith 1.0, a fine tune built on Qwen 3.5 397B A17B. Comes with mmproj for vision, but isn't shipped with MTP. You can use DFLASH with it, a novel diffusion based MTP-like, to speed up TG - comes in a variety of quants, you can download the one that works best for your model size.

DFLASH paper: https://arxiv.org/abs/2602.06036

Thanks to:

https://huggingface.co/z-lab/Qwen3.5-397B-A17B-DFlash

https://huggingface.co/modal-labs/Qwen3.5-397B-A17B-DFlash

https://huggingface.co/lmsys/Qwen3.5-397B-A17B-DFlash

Load DFLASH with:

--model-draft path/to/Ornith-DFLASH.gguf
--spec-type dflash:n_max=1,cross_ctx=256

All quants target 16/24/32GB GPUs, with varying amounts of RAM depending on the quant.

Specific quant details (memory footprint with mmproj, without MTP/DFLASH):

IQ4_K - for 256GB RAM + 24GB VRAM

Will eat 20180MB of VRAM and 198GB of RAM with standard config:

    ./build/bin/llama-server
    -m pmodels/Ornith-1.0-397B-A17B-IQ4_K.gguf
    --mmproj pmodels/Ornith-mmproj-BF16.gguf
    --mmproj-gpu-lazy
    -a Orinth
    --slot-save-path slots
    --context-shift off
    -ot "blk\.(?:[0-9]|[1-5][0-9])\.ffn.*_exps.*=CPU"
    -ot "token_embd\.weight=CPU"
    -c 200000
    --ctx-checkpoints 8
    --ctx-checkpoints-interval 0
    --ctx-checkpoints-tolerance 4
    --parallel 1
    -cram 0
    -b 4096 -ub 4096
    -wgt 1
    -ctk q8_0 -ctv q8_0
    -khad
    -mqkv
    --threads 15 --threads-batch 16 -ngl 100
    -cuda fusion=1,offload-batch-size=16,mmq-id-size=0,fa-offset=0
    --host 127.0.0.1
    --port 8080
    --webui none
    --jinja

Details:

  # 60 Repeating Layers [0-59] + MTP

  ## Gated Attention/Delta Net [Blended 0-59]
  blk\..*\.attn_gate\.weight=q8_0
  blk\..*\.attn_qkv\.weight=q8_0
  blk\..*\.ssm_alpha\.weight=bf16
  blk\..*\.ssm_beta\.weight=bf16
  blk\..*\.ssm_out\.weight=bf16

  # Normal attention
  blk\..*\.attn_output\.weight=q8_0
  blk\..*\.attn_q\.weight=q8_0
  blk\..*\.attn_k\.weight=q8_0
  blk\..*\.attn_v\.weight=q8_0

  # Shared Expert Layers [0-59]
  blk\..*\.ffn_down_shexp\.weight=q8_0
  blk\..*\.ffn_(gate|up)_shexp\.weight=q8_0

  # Routed Experts Layers [0-59]
  blk\..*\.ffn_down_exps\.weight=iq4_k
  blk\..*\.ffn_(gate|up)_exps\.weight=iq4_kss

  # Non-Repeating Layers
  token_embd\.weight=q8_0
  output\.weight=iq6_k

IQ4_KSS - for 256GB RAM + 24GB VRAM

Will eat 18826MB of VRAM and 191GB of RAM with standard config:

    ./build/bin/llama-server
    -m pmodels/Ornith-1.0-397B-A17B-IQ4_KSS.gguf
    --mmproj pmodels/Ornith-mmproj-BF16.gguf
    --mmproj-gpu-lazy
    -a Orinth
    --slot-save-path slots
    --context-shift off
    -ot "blk\.(?:[0-9]|[1-5][0-9])\.ffn.*_exps.*=CPU"
    -ot "token_embd\.weight=CPU"
    -c 200000
    --ctx-checkpoints 8
    --ctx-checkpoints-interval 0
    --ctx-checkpoints-tolerance 4
    --parallel 1
    -cram 0
    -b 4096 -ub 4096
    -wgt 1
    -ctk q8_0 -ctv q8_0
    -khad
    -mqkv
    --threads 15 --threads-batch 16 -ngl 100
    -cuda fusion=1,offload-batch-size=16,mmq-id-size=0,fa-offset=0
    --host 127.0.0.1
    --port 8080
    --webui none
    --jinja

Details:

  # 60 Repeating Layers [0-59] + MTP

  ## Gated Attention/Delta Net [Blended 0-59]
  blk\..*\.attn_gate\.weight=q8_0
  blk\..*\.attn_qkv\.weight=q8_0
  blk\..*\.ssm_alpha\.weight=bf16
  blk\..*\.ssm_beta\.weight=bf16
  blk\..*\.ssm_out\.weight=q8_0

  # Normal attention
  blk\..*\.attn_output\.weight=q8_0
  blk\..*\.attn_q\.weight=q8_0
  blk\..*\.attn_k\.weight=q8_0
  blk\..*\.attn_v\.weight=q8_0

  # Shared Expert Layers [0-59]
  blk\..*\.ffn_down_shexp\.weight=q8_0
  blk\..*\.ffn_(gate|up)_shexp\.weight=q8_0

  # Routed Experts Layers [0-59]
  blk\..*\.ffn_down_exps\.weight=iq4_kss
  blk\..*\.ffn_(gate|up)_exps\.weight=iq4_kss

  # Non-Repeating Layers
  token_embd\.weight=q8_0
  output\.weight=iq6_k

IQ3_KS - for 192GB RAM + 24GB VRAM

Will eat 17600MB of VRAM and 137GB of RAM with standard config:

    ./build/bin/llama-server
    -m pmodels/Ornith-1.0-397B-A17B-IQ3_KS.gguf
    --mmproj pmodels/Ornith-mmproj-BF16.gguf
    --mmproj-gpu-lazy
    -a Orinth
    --slot-save-path slots
    --context-shift off
    -ot "blk\.(?:[0-9]|[1-5][0-9])\.ffn.*_exps.*=CPU"
    -ot "token_embd\.weight=CPU"
    -c 200000
    --ctx-checkpoints 8
    --ctx-checkpoints-interval 0
    --ctx-checkpoints-tolerance 4
    --parallel 1
    -cram 0
    -b 4096 -ub 4096
    -wgt 1
    -ctk q8_0 -ctv q8_0
    -khad
    -mqkv
    --threads 15 --threads-batch 16 -ngl 100
    -cuda fusion=1,offload-batch-size=16,mmq-id-size=0,fa-offset=0
    --host 127.0.0.1
    --port 8080
    --webui none
    --jinja

Details:

  # 60 Repeating Layers [0-59] + MTP

  ## Gated Attention/Delta Net [Blended 0-59]
  blk\..*\.attn_gate\.weight=q8_0
  blk\..*\.attn_qkv\.weight=q8_0
  blk\..*\.ssm_alpha\.weight=bf16
  blk\..*\.ssm_beta\.weight=bf16
  blk\..*\.ssm_out\.weight=q8_0

  # Normal attention
  blk\..*\.attn_output\.weight=q8_0
  blk\..*\.attn_q\.weight=q8_0
  blk\..*\.attn_k\.weight=q8_0
  blk\..*\.attn_v\.weight=q8_0

  # Shared Expert Layers [0-59]
  blk\..*\.ffn_down_shexp\.weight=iq6_k
  blk\..*\.ffn_(gate|up)_shexp\.weight=iq6_k

  # Routed Experts Layers [0-59]
  blk\..*\.ffn_down_exps\.weight=iq3_ks
  blk\..*\.ffn_(gate|up)_exps\.weight=iq2_kl

  # Non-Repeating Layers
  token_embd\.weight=iq6_k
  output\.weight=iq6_k

IQ2_KS - for 128GB RAM + 16GB VRAM

Will eat 13988MB of VRAM and 92.4GB of RAM with standard config:

    ./build/bin/llama-server
    -m pmodels/Ornith-1.0-397B-A17B-IQ2_KS.gguf
    --mmproj pmodels/Ornith-mmproj-BF16.gguf
    --mmproj-gpu-lazy
    -a Orinth
    --slot-save-path slots
    --context-shift off
    -ot "blk\.(?:[0-9]|[1-5][0-9])\.ffn.*_exps.*=CPU"
    -ot "token_embd\.weight=CPU"
    -c 200000
    --ctx-checkpoints 8
    --ctx-checkpoints-interval 0
    --ctx-checkpoints-tolerance 4
    --parallel 1
    -cram 0
    -b 4096 -ub 4096
    -wgt 1
    -ctk q8_0 -ctv q8_0
    -khad
    -mqkv
    --threads 15 --threads-batch 16 -ngl 100
    -cuda fusion=1,offload-batch-size=16,mmq-id-size=0,fa-offset=0
    --host 127.0.0.1
    --port 8080
    --webui none
    --jinja

Details:

  # 60 Repeating Layers [0-59] + MTP

  ## Gated Attention/Delta Net [Blended 0-59]
  blk\..*\.attn_gate\.weight=iq4_ks
  blk\..*\.attn_qkv\.weight=iq4_ks
  blk\..*\.ssm_alpha\.weight=q8_0
  blk\..*\.ssm_beta\.weight=q8_0
  blk\..*\.ssm_out\.weight=q8_0

  # Normal attention
  blk\..*\.attn_output\.weight=iq4_kss
  blk\..*\.attn_q\.weight=iq4_kss
  blk\..*\.attn_k\.weight=iq4_kss
  blk\..*\.attn_v\.weight=iq4_kss

  # Shared Expert Layers [0-59]
  blk\..*\.ffn_down_shexp\.weight=iq4_kss
  blk\..*\.ffn_(gate|up)_shexp\.weight=iq4_kss

  # Routed Experts Layers [0-59]
  blk\..*\.ffn_down_exps\.weight=iq2_kt
  blk\..*\.ffn_(gate|up)_exps\.weight=iq1_kt

  # Non-Repeating Layers
  token_embd\.weight=iq4_ks
  output\.weight=iq4_ks

Every additional 65536 tokens of context window require one additional GB of VRAM at Q8 KV cache.

The model was natively trained on a 262144 ctx window, so if you want to go beyond 262144 you need to use the additional YARN commands (both for ik and mainline):

  --rope-scaling yarn
  --rope-scale N
  --yarn-orig-ctx 262144

Where N is the context ceiling multiplier (2 for 524288, 4 for 1M). Close to no quality loss at scale 2, some quality loss at scale 4.

Downloads last month: 2,515

GGUF

Model size

1B params

Architecture

dflash-draft

Hardware compatibility

2-bit

16-bit

View +3 variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF

Base model

deepreinforce-ai/Ornith-1.0-397B

Quantized

(13)

this model

Paper for paragon-of-brah/Ornith-1.0-397B-DFLASH-GGUF

DFlash: Block Diffusion for Flash Speculative Decoding

Paper • 2602.06036 • Published Feb 5 • 89