Instructions to use Frosty40/Ornith-1.0-35B-B70-Turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Frosty40/Ornith-1.0-35B-B70-Turbo with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Frosty40/Ornith-1.0-35B-B70-Turbo",
	filename="ornith-1.0-35b-Q5_K_M.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 Frosty40/Ornith-1.0-35B-B70-Turbo 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 Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_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 Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_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 Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_K_M

Use Docker

docker model run hf.co/Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_K_M

LM Studio
Jan

vLLM

How to use Frosty40/Ornith-1.0-35B-B70-Turbo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Frosty40/Ornith-1.0-35B-B70-Turbo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Frosty40/Ornith-1.0-35B-B70-Turbo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_K_M

Ollama
How to use Frosty40/Ornith-1.0-35B-B70-Turbo with Ollama:
```
ollama run hf.co/Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_K_M
```

Unsloth Studio

How to use Frosty40/Ornith-1.0-35B-B70-Turbo 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 Frosty40/Ornith-1.0-35B-B70-Turbo 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 Frosty40/Ornith-1.0-35B-B70-Turbo to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Frosty40/Ornith-1.0-35B-B70-Turbo to start chatting

How to use Frosty40/Ornith-1.0-35B-B70-Turbo with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_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": "Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Frosty40/Ornith-1.0-35B-B70-Turbo with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_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 Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Frosty40/Ornith-1.0-35B-B70-Turbo with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_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 "Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_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 Frosty40/Ornith-1.0-35B-B70-Turbo with Docker Model Runner:
```
docker model run hf.co/Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_K_M
```

Lemonade

How to use Frosty40/Ornith-1.0-35B-B70-Turbo with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Frosty40/Ornith-1.0-35B-B70-Turbo:Q5_K_M

Run and chat with the model

lemonade run user.Ornith-1.0-35B-B70-Turbo-Q5_K_M

List all available models

lemonade list

Ornith-1.0-35B B70 Turbo GGUF

This repository publishes a Q5_K_M GGUF for deepreinforce-ai/Ornith-1.0-35B plus the tested Intel Arc Pro B70 serving recipe.

The "Turbo" part is the serving stack, not a behavior-changing fine-tune:

same base model semantics as Ornith-1.0-35B
Q5_K_M GGUF quantization
llama.cpp SYCL runtime tuned for Intel Arc Pro B70
no safeguard edits, refusal edits, or new training
no speculative-head artifact in this release

For the benchmark package, raw tables, charts, and example games, see: newjordan/Ornith-1.0-35B-B70-Turbo.

Files

File	Purpose
`ornith-1.0-35b-Q5_K_M.gguf`	Q5_K_M GGUF model file
`ornith-1.0-35b-Q5_K_M.gguf.sha256`	SHA-256 checksum

Recommended B70 Serve Config

Agent-fleet default:

GGML_SYCL_DISABLE_DNN=1 ONEAPI_DEVICE_SELECTOR=level_zero:gpu \
llama-server \
  -m ornith-1.0-35b-Q5_K_M.gguf \
  --alias ornith-1.0-35b-turbo \
  -ngl 99 -fa on -ctk f16 -ctv f16 \
  -c 131072 -np 32 -b 8192 -ub 4096 \
  --host 0.0.0.0 --port 8092 --jinja

Single deep-agent profile:

GGML_SYCL_DISABLE_DNN=1 ONEAPI_DEVICE_SELECTOR=level_zero:gpu \
llama-server \
  -m ornith-1.0-35b-Q5_K_M.gguf \
  --alias ornith-1.0-35b-turbo \
  -ngl 99 -fa on -ctk f16 -ctv f16 \
  -c 262144 -np 1 -b 8192 -ub 4096 \
  --host 0.0.0.0 --port 8092 --jinja

Avoid -np >= 56 on a single B70 in the measured fleet harness; it thrashed or timed out under the tested workload.

Measured Performance

Hardware and stack:

GPU: Intel Arc Pro B70, 30.3 GiB, 230 W
Runtime: llama.cpp SYCL
Quant: Q5_K_M
KV cache in the final ship profile: f16

The benchmark split compares:

upstream: mainline llama.cpp, default flags
up+flags: mainline llama.cpp plus B70 runtime flags
Turbo: B70 fusion build plus the same runtime flags

Prefill

The tuned runtime configuration provides most of the prefill win.

Prompt tokens	upstream	up+flags	Turbo	Total win
805	1075	1378	1386	1.29x
3313	1074	1840	1846	1.72x
6963	1031	1741	1734	1.68x
14563	959	1538	1531	1.60x
29713	825	1208	1205	1.46x
61341	628	828	826	1.32x
129325	413	489	488	1.18x

Single-Stream Decode

The B70 fusion build provides the single-stream decode gain.

Context depth	upstream	up+flags	Turbo	Total win
805	81.7	81.8	93.5	1.14x
3313	80.0	79.8	91.2	1.14x
6963	77.5	77.4	88.2	1.14x
14563	72.9	72.7	82.3	1.13x
29713	66.5	66.1	74.1	1.11x
61341	55.7	55.5	61.1	1.10x
129325	41.4	41.3	44.2	1.07x

Fleet Decode

Aggregate decode with a synthetic 2048+256 workload:

Agents	upstream	up+flags	Turbo	Total win
1	78.5	78.9	86.2	1.10x
4	85.7	118.8	120.8	1.41x
8	91.4	132.8	132.8	1.45x
16	98.1	132.3	132.5	1.35x
24	103.2	143.8	139.0	1.35x
32	112.0	149.1	149.1	1.33x
48	122.9	160.8	157.0	1.28x
56	126.6	161.8	160.2	1.27x

Accuracy Snapshot

These are reference lm-eval results carried over from the local benchmark set; serving changes are lossless for the same GGUF.

Benchmark	Score
GSM8K	97.0
HellaSwag	82.1
Winogrande	71.6
ARC-Challenge	49.2
MMLU	41.1
TruthfulQA-MC1	35.7
Wikitext2 PPL	6.36

Notes

This release is for llama.cpp-compatible GGUF runtimes.
The best measured B70 profile uses f16 KV. q8_0 KV was slower at long depth on this SYCL backend in local testing.
The route-aware DeepSpec/Eagle3 speculative-head work is tracked separately and is not included in this artifact.

Downloads last month: 88

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

5-bit

Model tree for Frosty40/Ornith-1.0-35B-B70-Turbo

Base model

deepreinforce-ai/Ornith-1.0-35B

Quantized

(146)

this model