Instructions to use Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4 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/Leanstral-1.5-119B-A6B-GGUF-NVFP4:NVFP4
# Run inference directly in the terminal:
llama cli -hf Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4:NVFP4
# Run inference directly in the terminal:
llama cli -hf Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4:NVFP4

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/Leanstral-1.5-119B-A6B-GGUF-NVFP4:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4:NVFP4

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/Leanstral-1.5-119B-A6B-GGUF-NVFP4:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4:NVFP4

Use Docker

docker model run hf.co/Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4:NVFP4

LM Studio
Jan
Ollama
How to use Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4 with Ollama:
```
ollama run hf.co/Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4:NVFP4
```

Unsloth Studio

How to use Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4 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/Leanstral-1.5-119B-A6B-GGUF-NVFP4 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/Leanstral-1.5-119B-A6B-GGUF-NVFP4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4 to start chatting

Docker Model Runner
How to use Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4 with Docker Model Runner:
```
docker model run hf.co/Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4:NVFP4
```

Lemonade

How to use Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Frosty40/Leanstral-1.5-119B-A6B-GGUF-NVFP4:NVFP4

Run and chat with the model

lemonade run user.Leanstral-1.5-119B-A6B-GGUF-NVFP4-NVFP4

List all available models

lemonade list

Atomic Chat

Leanstral-1.5-119B-A6B-GGUF-NVFP4 / assets /benchmark-throughput.svg

Frosty40

Add benchmark throughput graph

3a8521b verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

5.25 kB

	<svg xmlns="http://www.w3.org/2000/svg" width="1280" height="640" viewBox="0 0 1280 640">
	<rect width="1280" height="640" rx="24" fill="#0b0f19"/>
	<rect x="28" y="28" width="1224" height="584" rx="18" fill="#111827" stroke="#253044"/>
	<text x="64" y="70" fill="#e5e7eb" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="28" font-weight="700">Leanstral NVFP4 llama-bench</text>
	<text x="64" y="102" fill="#94a3b8" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="16">NVIDIA GB10, CUDA, -ngl 99, f16 KV, 3 repetitions</text>
	<line x1="120" y1="512.0" x2="1224" y2="512.0" stroke="#253044" stroke-width="1"/>
	<text x="102" y="517.0" text-anchor="end" fill="#94a3b8" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="14">0</text>
	<line x1="120" y1="438.0" x2="1224" y2="438.0" stroke="#253044" stroke-width="1"/>
	<text x="102" y="443.0" text-anchor="end" fill="#94a3b8" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="14">220</text>
	<line x1="120" y1="364.0" x2="1224" y2="364.0" stroke="#253044" stroke-width="1"/>
	<text x="102" y="369.0" text-anchor="end" fill="#94a3b8" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="14">440</text>
	<line x1="120" y1="290.0" x2="1224" y2="290.0" stroke="#253044" stroke-width="1"/>
	<text x="102" y="295.0" text-anchor="end" fill="#94a3b8" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="14">660</text>
	<line x1="120" y1="216.0" x2="1224" y2="216.0" stroke="#253044" stroke-width="1"/>
	<text x="102" y="221.0" text-anchor="end" fill="#94a3b8" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="14">880</text>
	<line x1="120" y1="142.0" x2="1224" y2="142.0" stroke="#253044" stroke-width="1"/>
	<text x="102" y="147.0" text-anchor="end" fill="#94a3b8" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="14">1100</text>
	<rect x="166.4" y="204.0" width="128.1" height="308.0" rx="10" fill="#f6c453" opacity="0.92"/>
	<line x1="230.4" y1="194.1" x2="230.4" y2="214.0" stroke="#e5e7eb" stroke-width="3" stroke-linecap="round"/>
	<text x="230.4" y="190.0" text-anchor="middle" fill="#e5e7eb" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="18" font-weight="700">915.53</text>
	<text x="230.4" y="564" text-anchor="middle" fill="#e5e7eb" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="17" font-weight="600">pp512</text>
	<text x="230.4" y="588" text-anchor="middle" fill="#94a3b8" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="14">+/- 29.72</text>
	<rect x="387.2" y="154.2" width="128.1" height="357.8" rx="10" fill="#38bdf8" opacity="0.92"/>
	<line x1="451.2" y1="145.6" x2="451.2" y2="162.8" stroke="#e5e7eb" stroke-width="3" stroke-linecap="round"/>
	<text x="451.2" y="140.2" text-anchor="middle" fill="#e5e7eb" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="18" font-weight="700">1063.67</text>
	<text x="451.2" y="564" text-anchor="middle" fill="#e5e7eb" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="17" font-weight="600">pp2048</text>
	<text x="451.2" y="588" text-anchor="middle" fill="#94a3b8" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="14">+/- 25.59</text>
	<rect x="608.0" y="496.2" width="128.1" height="15.8" rx="10" fill="#34d399" opacity="0.92"/>
	<line x1="672.0" y1="496.1" x2="672.0" y2="496.4" stroke="#e5e7eb" stroke-width="3" stroke-linecap="round"/>
	<text x="672.0" y="482.2" text-anchor="middle" fill="#e5e7eb" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="18" font-weight="700">46.87</text>
	<text x="672.0" y="564" text-anchor="middle" fill="#e5e7eb" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="17" font-weight="600">tg128</text>
	<text x="672.0" y="588" text-anchor="middle" fill="#94a3b8" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="14">+/- 0.47</text>
	<rect x="828.8" y="445.7" width="128.1" height="66.3" rx="10" fill="#f472b6" opacity="0.92"/>
	<line x1="892.8" y1="444.6" x2="892.8" y2="446.8" stroke="#e5e7eb" stroke-width="3" stroke-linecap="round"/>
	<text x="892.8" y="431.7" text-anchor="middle" fill="#e5e7eb" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="18" font-weight="700">197.10</text>
	<text x="892.8" y="564" text-anchor="middle" fill="#e5e7eb" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="17" font-weight="600">pp512+tg128</text>
	<text x="892.8" y="588" text-anchor="middle" fill="#94a3b8" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="14">+/- 3.19</text>
	<rect x="1049.6" y="359.3" width="128.1" height="152.7" rx="10" fill="#f6c453" opacity="0.92"/>
	<line x1="1113.6" y1="358.3" x2="1113.6" y2="360.3" stroke="#e5e7eb" stroke-width="3" stroke-linecap="round"/>
	<text x="1113.6" y="345.3" text-anchor="middle" fill="#e5e7eb" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="18" font-weight="700">454.02</text>
	<text x="1113.6" y="564" text-anchor="middle" fill="#e5e7eb" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="17" font-weight="600">pp2048+tg128</text>
	<text x="1113.6" y="588" text-anchor="middle" fill="#94a3b8" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="14">+/- 2.99</text>
	<text x="54" y="327.0" text-anchor="middle" fill="#94a3b8" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="15" transform="rotate(-90 54 327.0)">tokens / second</text>
	</svg>