Instructions to use LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1",
	filename="ornith-1.0-35b-IQ4_XS-MTP-graft-headQ6.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1 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 LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M

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 LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M

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 LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M

Use Docker

docker model run hf.co/LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M

LM Studio
Jan

vLLM

How to use LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M

Ollama
How to use LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1 with Ollama:
```
ollama run hf.co/LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M
```

Unsloth Studio

How to use LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1 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 LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1 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 LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1 to start chatting

How to use LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M

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": "LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M

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 LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M

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 "LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M" \
  --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"

Docker Model Runner
How to use LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1 with Docker Model Runner:
```
docker model run hf.co/LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M
```

Lemonade

How to use LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q4_K_M

Run and chat with the model

lemonade run user.Ornith-1.0-35B-GGUF-llamacpp-tp1-Q4_K_M

List all available models

lemonade list

Ornith-1.0-35B-GGUF-llamacpp-tp1 / configs /serving_profiles.yaml

LordNeel

Add machine-readable serving profile catalog

7c01a4f verified 25 days ago

Raw

History Blame Contribute Delete

5.43 kB

	model:
	hf_repo: deepreinforce-ai/Ornith-1.0-35B
	release_repo: LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1
	served_name: Ornith-1.0-35B

	policy:
	serving_parallelism: tp1_only
	tensor_parallel_size: 1
	backend: llama.cpp
	reasoning: "off"
	gpu_usage_note: Use one independent model copy per GPU. Do not split one serving replica across GPUs.
	forbidden:
	- tensor_parallel_size_gt_1
	- multi_gpu_serving

	default_profile: llamacpp_q4_k_m_coding_context
	lowest_memory_profile: llamacpp_q3_k_m_short_context
	middle_footprint_profile: llamacpp_iq4_xs_short_context
	adaptive_mtp_profile: llamacpp_iq4_xs_mtp_graft_adaptive

	profiles:
	- id: llamacpp_q4_k_m_short_context
	status: recommended_speed_benchmark
	backend: llama.cpp
	tensor_parallel_size: 1
	artifact: ornith-1.0-35b-Q4_K_M.gguf
	quant: Q4_K_M
	command:
	script: scripts/serve_llamacpp_gpu0.sh
	env:
	QUANT: Q4_K_M
	PORT: "8002"
	CTX_SIZE: "8192"
	PARALLEL: "16"
	BATCH_SIZE: "4096"
	UBATCH_SIZE: "512"
	REASONING: "off"
	measured:
	loaded_vram_gib: 21.31
	c1_output_tps: 243.3
	c16_output_tps: 655.6
	c16_p95_ttft_ms: 650.0
	behavior_gate: pass
	evidence:
	benchmark: benchmarks/llamacpp-quant-benchmarks.md
	behavior: probes/behavior-llamacpp-q4-script-default.json
	notes:
	- Short-context benchmark profile exposes about 512 tokens per slot because CTX_SIZE is split across PARALLEL slots.

	- id: llamacpp_q4_k_m_coding_context
	status: recommended_default
	backend: llama.cpp
	tensor_parallel_size: 1
	artifact: ornith-1.0-35b-Q4_K_M.gguf
	quant: Q4_K_M
	command:
	script: scripts/serve_llamacpp_gpu0.sh
	env:
	QUANT: Q4_K_M
	PORT: "8002"
	CTX_SIZE: "131072"
	PARALLEL: "16"
	BATCH_SIZE: "4096"
	UBATCH_SIZE: "512"
	REASONING: "off"
	measured:
	loaded_vram_gib_short_context: 21.31
	c16_output_tps_short_context: 655.6
	behavior_gate: pass
	evidence:
	benchmark: benchmarks/llamacpp-quant-benchmarks.md
	behavior: probes/behavior-llamacpp-q4-script-default.json
	notes:
	- Practical coding-serving profile with 16 slots and about 8k context per slot.
	- Throughput numbers come from the matched short-context sweep.

	- id: llamacpp_q3_k_m_short_context
	status: lowest_memory_validated
	backend: llama.cpp
	tensor_parallel_size: 1
	artifact: ornith-1.0-35b-Q3_K_M.gguf
	quant: Q3_K_M
	command:
	script: scripts/serve_llamacpp_gpu0.sh
	env:
	QUANT: Q3_K_M
	PORT: "8002"
	CTX_SIZE: "8192"
	PARALLEL: "16"
	BATCH_SIZE: "4096"
	UBATCH_SIZE: "512"
	REASONING: "off"
	measured:
	gguf_gib: 15.61
	loaded_vram_gib: 17.27
	c1_output_tps: 240.5
	c16_output_tps: 493.0
	mean_kld_nats_vs_bf16_top64: 0.3620
	behavior_gate: pass
	evidence:
	benchmark: benchmarks/llamacpp-quant-benchmarks.md
	kld: benchmarks/kld-quant-vs-bf16-top64.md
	behavior: probes/behavior-llamacpp-q3-k-m-parallel16.json

	- id: llamacpp_iq4_xs_short_context
	status: middle_footprint_validated
	backend: llama.cpp
	tensor_parallel_size: 1
	artifact: ornith-1.0-35b-IQ4_XS.gguf
	quant: IQ4_XS
	command:
	script: scripts/serve_llamacpp_gpu0.sh
	env:
	QUANT: IQ4_XS
	PORT: "8002"
	CTX_SIZE: "8192"
	PARALLEL: "16"
	BATCH_SIZE: "4096"
	UBATCH_SIZE: "512"
	REASONING: "off"
	measured:
	gguf_gib: 17.64
	loaded_vram_gib: 19.34
	c1_output_tps: 234.1
	c16_output_tps: 476.0
	mean_kld_nats_vs_bf16_top64: 0.1426
	behavior_gate: pass
	evidence:
	benchmark: benchmarks/llamacpp-quant-benchmarks.md
	kld: benchmarks/kld-quant-vs-bf16-top64.md
	behavior: probes/behavior-llamacpp-iq4-xs-parallel16.json

	- id: llamacpp_iq4_xs_mtp_graft_adaptive
	status: experimental_adaptive_mtp
	backend: llama.cpp
	tensor_parallel_size: 1
	artifact: ornith-1.0-35b-IQ4_XS-MTP-graft-headQ6.gguf
	quant: IQ4_XS_with_Q6_MTP_head
	command:
	script: scripts/serve_llamacpp_gpu0.sh
	env:
	MODEL_PATH: ornith-1.0-35b-IQ4_XS-MTP-graft-headQ6.gguf
	ALIAS: Ornith-1.0-35B-GGUF-IQ4_XS-MTP
	PORT: "8002"
	CTX_SIZE: "8192"
	PARALLEL: "16"
	BATCH_SIZE: "4096"
	UBATCH_SIZE: "512"
	REASONING: "off"
	SPEC_TYPE: draft-mtp
	SPEC_DRAFT_N_MAX: "2"
	SPEC_DRAFT_N_MIN: "0"
	SPEC_DRAFT_BACKEND_SAMPLING: "1"
	LLAMA_SPEC_MAX_DRAFTING_SLOTS: "1"
	LLAMA_MTP_FAST_BACKEND_SAMPLE: "1"
	LLAMA_MTP_DRAFT_TOP_K: "1"
	LLAMA_MTP_DRAFT_TOP_P: "1"
	LLAMA_MTP_DRAFT_TEMP: "1"
	measured:
	c1_ar_tps: 221.80
	c1_mtp_adaptive_tps: 319.53
	c1_acceptance_by_position:
	- 0.953
	- 0.865
	c16_ar_tps: 568.57
	c16_adaptive_tps: 564.48
	c16_threshold1_tps: 592.45
	evidence:
	benchmark: benchmarks/llamacpp-iq4-xs-mtp-graft-adaptive-profile.md
	patch: patches/llamacpp-mtp-adaptive-serving-and-recurrent-rollback.patch
	caveats:
	- Always-on MTP is not recommended at saturated c16 because it was slower than target-only decoding.
	- Adaptive throttling uses MTP for low-concurrency requests and disables it under saturated batches.