Unverified50% confidenceFactExact time
The 8-bit version of the Spark X 2.5 model file is approximately 4 GB, and the full-precision version is approximately 8 GB
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/27/2026
First Seen
Valid until: 12/26/2026
Sources
Related Entities
Related Claims
UnverifiedFor 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 GB79% similarUnverifiedThe combined unified memory of two DGX Sparks totals approximately 256 GB.71% similarUnverifiedThe DGX Spark is equipped with up to 128 GB of unified memory, AI compute performance of up to 1 petaFLOPS (FP4 precision), and is priced at approximately $3,000.69% similarUnverifiedThe UD-Q8_K_XL quantized version of DeepSeek V4 Flash has a file size of 162 GB, uses MXFP4+BF16 mixed precision, and achieves completely lossless quality.69% similarUnverifiedThe NVIDIA DGX Spark is equipped with the GB10 Grace Blackwell Superchip and 128 GB of unified memory.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/954248API
curl https://kongchang.com/api/v1/knowledge/claims/954248MCP
get_claim(id=954248)