[KongchangAI]
Unverified50% confidenceSolutionExact time

It is recommended to start with a 16K context rather than 1M, because the KV cache, video frames, and the 1.73 GB BF16 mmproj all come out of the same memory budget; video processing also requires ffmpeg and ffprobe in PATH.

1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027

Sources

Running Nemotron 3.5 Super VL Locally: 128GB of RAM Matters More Than Blackwell

Related Entities

llama.cppproductffmpegproductffprobeproduct

Related Claims

UnverifiedVideo generation models in their original FP16 format may require more than 20GB of VRAM, which can be compressed to under 5GB after Q4 quantization.71% similar

Cite This Claim

Stable URI
https://kongchang.com/claim/1049461
API
curl https://kongchang.com/api/v1/knowledge/claims/1049461
MCP
get_claim(id=1049461)