Instructions to use PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF",
	filename="DeepSeek-R1-Distill-Llama-70B-NVFP4.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama-cli -hf PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama-cli -hf PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF: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 PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF: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 PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF:NVFP4

Use Docker

docker model run hf.co/PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF:NVFP4

LM Studio
Jan

vLLM

How to use PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-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": "PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF:NVFP4

Ollama
How to use PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF with Ollama:
```
ollama run hf.co/PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF:NVFP4
```

Unsloth Studio new

How to use PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-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 PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-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 PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF to start chatting

Docker Model Runner
How to use PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF:NVFP4
```

Lemonade

How to use PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF:NVFP4

Run and chat with the model

lemonade run user.DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF-NVFP4

List all available models

lemonade list

DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF

NVFP4 GGUF of DeepSeek-R1-Distill-Llama-70B, optimized for NVIDIA Blackwell GPUs (RTX 5090, RTX PRO 6000, B200).

Overview

Property	Value
Base model	deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Quantization	NVFP4 (W4A4 — FP4 E2M1 weights, FP8 E4M3 block scales, FP32 global scales)
Format	GGUF (GGML_TYPE_NVFP4, type 40)
Size	42.7 GB
BPW	~4.84 bits per weight
Requires	NVIDIA Blackwell GPU (SM 120) for native FP4 tensor core acceleration
Speed	33.6 tok/s generation on RTX PRO 6000 96GB (single GPU)

Quantization Pipeline

This model was quantized using a custom pipeline:

Quantization tool: vllm-project/llm-compressor v0.10.0.2
Calibration: 128 samples from ultrachat-200k (train_sft split), max_seq_length 2048

Recipe:

QuantizationModifier:
  targets: [Linear]
  ignore: [lm_head]
  scheme: NVFP4

GGUF conversion: llama.cpp PR #21095 branch with two critical fixes:
- Tensor renaming: weight_packed → weight, weight_global_scale → weight_scale_2, input_global_scale → input_scale
- Scale inversion: llm-compressor stores weight_global_scale as a large divisor; ggml expects a small multiplier. Fix: store 1.0 / weight_global_scale in the GGUF .scale tensor.

Important: Scale Inversion Fix

If you're converting your own llm-compressor NVFP4 checkpoints to GGUF, you must invert the per-tensor global scale. llm-compressor stores scales like 4320.0 (divide by this to dequantize), while ggml's convention expects 0.000231 (multiply by this). Without this fix, the model loads and runs but produces garbage output.

In convert_hf_to_gguf.py, change:

self._write_scale_tensor(new_name.replace(".weight", ".scale"), scale2)

to:

self._write_scale_tensor(new_name.replace(".weight", ".scale"), 1.0 / scale2.float())

Provenance

Component	Source
Original base model	deepseek-ai/DeepSeek-R1-Distill-Llama-70B
NVFP4 checkpoint	PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4
GGUF conversion tooling	llama.cpp (PR #21095)
Quantization hardware	NVIDIA RTX PRO 6000 Blackwell 96GB

Usage

llama-server

./llama-server \
  -m DeepSeek-R1-Distill-Llama-70B-NVFP4.gguf \
  --host 0.0.0.0 \
  --port 8082 \
  -ngl 999

llama-cli

./llama-cli \
  -m DeepSeek-R1-Distill-Llama-70B-NVFP4.gguf \
  -ngl 999 \
  -c 8192 \
  --jinja \
  -p "What is the meaning of life?"

Benchmarks

Tested on RTX PRO 6000 Blackwell 96GB, llama.cpp b9037:

Metric	Value
Prompt eval	196.5 tok/s
Generation	33.6 tok/s
Context	131072 (default)
Parallel slots	4 (default)
VRAM usage	~80 GiB (model + KV cache at 131K context)

Comparison

Backend	tok/s
llama.cpp (this GGUF)	33.6
vLLM 0.19.0 (compressed-tensors)	25.0

Known Issues

This is a community conversion, not an official upstream release.
The NVFP4 GGUF ecosystem is still maturing. See llama.cpp Discussion #22042 for the ongoing discussion about NVFP4 scale handling.
Blackwell-native tensor core dispatch (PR #22196) may improve performance further when merged.

Credits

Quantized and converted by PiehSoft (William Pieh). Built on work by the llama.cpp community, particularly PR #21095 for NVFP4 GGUF conversion support.

Downloads last month: 506

GGUF

Model size

71B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for PiehSoft/DeepSeek-R1-Distill-Llama-70B-NVFP4-GGUF

Base model

deepseek-ai/DeepSeek-R1-Distill-Llama-70B

Quantized

(65)

this model