You can deploy this model and start earning money today!

Firworks/
Void-Citrus-L3.3-70B-fp8

Name: Void-Citrus-L3.3-70B-fp8
Availability: InStock

Darkknight535/Void-Citrus-L3.3-70B

quantized

compressed-tensors

Views

No views yet

Void-Citrus-L3.3-70B-fp8

Format: FP8_DYNAMIC — weights quantized to FP8 statically; activations scaled dynamically at runtime.
Base model: Darkknight535/Void-Citrus-L3.3-70B
How it was made: One-shot datafree quantization with LLM Compressor (FP8_DYNAMIC recipe) on a DGX Spark (GB10 Grace Blackwell). No calibration data required — activations are scaled dynamically at runtime.

Notes: lm_head and multimodal projection layers kept in high precision. Blackwell (GB10/B100/B200) has native FP8 hardware support. Hopper (H100/H200) also supports FP8 natively. Older architectures will fall back to BF16 compute while still benefiting from the reduced model size.

Check the original model card for information about this model.

Running the model with vLLM in Docker

sudo docker run --runtime nvidia --gpus all -p 8000:8000 --ipc=host \
  vllm/vllm-openai:latest \
  --model Firworks/Void-Citrus-L3.3-70B-fp8 \
  --dtype auto \
  --max-model-len 32768

Specifically for the DGX Spark

sudo docker run --gpus all --network host --ipc=host \
  nvcr.io/nvidia/vllm:26.02-py3 \
  vllm serve firworks/Void-Citrus-L3.3-70B-fp8 \
  --dtype auto \
  --max-model-len 32768

Tested on a DGX Spark (GB10 Grace Blackwell Superchip, 128GB unified memory).

If there are other models you'd like quantized to FP8, let me know.