Sponsored by APIMart
Toolify Toolify logo
AI Models
DeepSeek-R1-NVFP4-FP8-BLOCK

inference-optimization / DeepSeek-R1-NVFP4-FP8-BLOCK

Run on huggingface.co
huggingface.co
Total runs: 52
24-hour runs: 0
7-day runs: 2
30-day runs: 2
Model's Last Updated: March 13 2026

Introduction of DeepSeek-R1-NVFP4-FP8-BLOCK

Model Details of DeepSeek-R1-NVFP4-FP8-BLOCK

Model Overview

Description:

Model created from the nvidia/DeepSeek-R1-NVFP4 checkpoint by:

  • converting all layers targeted by modelopt NVFP4 format to compressed-tensors format
  • applying FP8_BLOCK quantization to targeted attention layers

More information at https://github.com/vllm-project/llm-compressor/pull/2228

Runs successfully on 4 B200s: 

from vllm import LLM, SamplingParams

prompts = ["The Swiss Alps are", "Brad Marchand is", "The Toronto Maple Leafs are"]

# Create a sampling params object for greedy sampling
sampling_params = SamplingParams(
    temperature=0.80, top_p=0.95, max_tokens=40, min_tokens=10
)
llm = LLM(
    "inference-optimization/DeepSeek-R1-NVFP4-FP8-BLOCK",
    tensor_parallel_size=4,
    max_model_len=4096,
    enforce_eager=True,
)
output = llm.generate(prompts, sampling_params)
for out in output:
    print(out.outputs[0].text)

Runs of inference-optimization DeepSeek-R1-NVFP4-FP8-BLOCK on huggingface.co

52
Total runs
0
24-hour runs
0
3-day runs
2
7-day runs
2
30-day runs

More Information About DeepSeek-R1-NVFP4-FP8-BLOCK huggingface.co Model

More DeepSeek-R1-NVFP4-FP8-BLOCK license Visit here:

https://choosealicense.com/licenses/mit

DeepSeek-R1-NVFP4-FP8-BLOCK huggingface.co

DeepSeek-R1-NVFP4-FP8-BLOCK huggingface.co is an AI model on huggingface.co that provides DeepSeek-R1-NVFP4-FP8-BLOCK's model effect (), which can be used instantly with this inference-optimization DeepSeek-R1-NVFP4-FP8-BLOCK model. huggingface.co supports a free trial of the DeepSeek-R1-NVFP4-FP8-BLOCK model, and also provides paid use of the DeepSeek-R1-NVFP4-FP8-BLOCK. Support call DeepSeek-R1-NVFP4-FP8-BLOCK model through api, including Node.js, Python, http.

DeepSeek-R1-NVFP4-FP8-BLOCK huggingface.co Url

https://huggingface.co/inference-optimization/DeepSeek-R1-NVFP4-FP8-BLOCK

inference-optimization DeepSeek-R1-NVFP4-FP8-BLOCK online free

DeepSeek-R1-NVFP4-FP8-BLOCK huggingface.co is an online trial and call api platform, which integrates DeepSeek-R1-NVFP4-FP8-BLOCK's modeling effects, including api services, and provides a free online trial of DeepSeek-R1-NVFP4-FP8-BLOCK, you can try DeepSeek-R1-NVFP4-FP8-BLOCK online for free by clicking the link below.

inference-optimization DeepSeek-R1-NVFP4-FP8-BLOCK online free url in huggingface.co:

https://huggingface.co/inference-optimization/DeepSeek-R1-NVFP4-FP8-BLOCK

DeepSeek-R1-NVFP4-FP8-BLOCK install

DeepSeek-R1-NVFP4-FP8-BLOCK is an open source model from GitHub that offers a free installation service, and any user can find DeepSeek-R1-NVFP4-FP8-BLOCK on GitHub to install. At the same time, huggingface.co provides the effect of DeepSeek-R1-NVFP4-FP8-BLOCK install, users can directly use DeepSeek-R1-NVFP4-FP8-BLOCK installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

DeepSeek-R1-NVFP4-FP8-BLOCK install url in huggingface.co:

https://huggingface.co/inference-optimization/DeepSeek-R1-NVFP4-FP8-BLOCK

Url of DeepSeek-R1-NVFP4-FP8-BLOCK

Provider of DeepSeek-R1-NVFP4-FP8-BLOCK huggingface.co

inference-optimization
ORGANIZATIONS
huggingface.co

Other API from inference-optimization