Instructions to use Ninnix96/Ornith-1.5-35B-A3B-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Ninnix96/Ornith-1.5-35B-A3B-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 Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K
# Run inference directly in the terminal:
llama cli -hf Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K
# Run inference directly in the terminal:
llama cli -hf Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K
# Run inference directly in the terminal:
./build/bin/llama cli -hf Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K

Use Docker

docker model run hf.co/Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K

Llama new
LM Studio
Jan

vLLM

How to use Ninnix96/Ornith-1.5-35B-A3B-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ninnix96/Ornith-1.5-35B-A3B-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ninnix96/Ornith-1.5-35B-A3B-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K

Ollama
How to use Ninnix96/Ornith-1.5-35B-A3B-gguf with Ollama:
```
ollama run hf.co/Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K
```
Unsloth Desktop

How to use Ninnix96/Ornith-1.5-35B-A3B-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Ninnix96/Ornith-1.5-35B-A3B-gguf with Docker Model Runner:
```
docker model run hf.co/Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K
```

Lemonade

How to use Ninnix96/Ornith-1.5-35B-A3B-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K

Run and chat with the model

lemonade run user.Ornith-1.5-35B-A3B-gguf-Q2_K

List all available models

lemonade list

Hermes Agent

How to use Ninnix96/Ornith-1.5-35B-A3B-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 Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K

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 Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Ninnix96/Ornith-1.5-35B-A3B-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Ninnix96/Ornith-1.5-35B-A3B-gguf:Q2_K" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

antirez-recipe quants

MoE quants following the antirez recipe: routed experts quantized hard, everything else protected.

Tensor class	Quant	Notes
`blk..ffn_gate_exps`, `blk..ffn_up_exps` (`ffn_gate_up_exps` if fused)	GU_TYPE (imatrix)	routed-expert gate/up
`blk.*.ffn_down_exps`	DOWN_TYPE (imatrix)	routed-expert down (K-quant for quality)
`blk..ffn_{gate,up,down}_shexp`, all `attn_`, `output.weight`	`Q8_0`	shared experts / attention / head
`token_embd.weight`	`F16`	embeddings
router (`ffn_gate_inp`), norms, sinks, biases	source precision (`BF16`/`F32`)	never quantized by llama.cpp

Base type Q8_0 + --tensor-type overrides, imatrix calibration (see SPEC per-model imatrix links). Runs on upstream llama.cpp — no fork or patch needed.

Validation per file: gguf-dump tensor audit (experts = GU/DOWN, protection intact), llama-cli smoke load, llama-perplexity spot ppl + --kl-divergence vs BF16 logits.

Files

File	Size	SHA-256
`Ornith-1.5-35B-A3B-Q2-IQ2_XXS-Q2_K.gguf`	14215041696	`f6848c148c1d4644f103c0e1b735545c262f9779f83e9489b95235fadb345916`

Imatrix: https://huggingface.co/mradermacher/Ornith-1.5-35B-A3B-i1-GGUF

Recipe

Antirez recipe on ornith-ai/Ornith-1.5-35B-A3B (BF16 source, ornith-ai/Ornith-1.5-35B-A3B):

ffn_gate_exps / ffn_up_exps / ffn_gate_up_exps -> IQ2_XXS
ffn_down_exps -> Q2_K
attention + shared experts + repr-MTP blocks blk.38/39/40 + output -> Q8_0
token embeddings -> F16
imatrix: mradermacher/Ornith-1.5-35B-A3B-i1-GGUF

Notes: mradermacher's imatrix does not cover the MTP/draft blocks (blk.38-40); they are forced to Q8_0 with a first-position llama-quantize rule (first matching regex wins). ~14.2 GB, about 2.9 BPW.

Validation (llama.cpp, qwen35moe arch)

12-case hard-smoke eval (temp 0, ctx 15360, model's own embedded chat template): 9/12 PASS; ~27 t/s generation (AMD Vulkan/UMA); fails cases 10567, 1606, juliet-cwe121. Passes both big-code cases.
Exact output tokens (own tokenizer) over the 9 solved: 51,528 = 5,725 tok/solved.
KL divergence vs official ornith-ai Q8_0 (ds4 short prompts, ctx 60, 2 chunks, CPU): per-chunk KL 0.214 / 0.262 (avg 0.238), delta-p RMS ~10.8%, same-token top-1 86.2 / 81.0%.

Downloads last month: 178

GGUF

Model size

36B params

Architecture

qwen35moe

Hardware compatibility

2-bit

Model tree for Ninnix96/Ornith-1.5-35B-A3B-gguf

Base model

ornith-ai/Ornith-1.5-35B-A3B

Quantized

(208)

this model

Collection including Ninnix96/Ornith-1.5-35B-A3B-gguf

Antirez's MoE recipe

Collection

Antirez recipe for MoE quantization: Q2 uses IQ2_XXS gate/up + Q2_K down; Q4 uses Q4_K gate/up + MXFP4 down. Everything else almost unchanged. • 10 items • Updated 9 days ago