Partially Verified80% confidenceFactExact time
The 816B-parameter Muse Spark Open occupies about 493GB of memory after NVFP4 quantization, while FP16 storage would require more than 1.6TB.
4
Sources
80%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRunning the BF16 checkpoint of Muse Spark Open requires about 2 TB of VRAM, equivalent to a cluster of 32 H200 GPUs; the NVFP4 (4-bit) checkpoint reduces the requirement to about 530 GB, validated on four NVIDIA Blackwell Ultra GPUs or eight H200s.77% similarUnverifiedNVIDIA released an NVFP4 quantized model of Qwen3 235B on Hugging Face, compressing the model from approximately 470 GB of VRAM in BF16 to approximately 156 GB, enabling it to run on a single-node cluster of 8 H100 GPUs.71% similarUnverifiedFor Spark X 2.5, at 32,000 tokens the KV cache is approximately 1.3 GB with a total footprint of approximately 9 GB; at 128,000 tokens the KV cache is approximately 4.9 GB; and at 1 million tokens the KV cache is approximately 39 GB plus a model file of approximately 43 GB71% similarVerifiedRunning Muse Glimmer at full precision requires 55 GB of VRAM, which is compressed to under 20 GB via 4-bit quantization, allowing it to run on consumer-grade GPUs with 24 GB of VRAM.70% similarUnverifiedThe BF16 weight files for Naive-N0.5-Flash are approximately 618GB, and the FP8 format version weights are approximately 315GB69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1038320API
curl https://kongchang.com/api/v1/knowledge/claims/1038320MCP
get_claim(id=1038320)