Unverified50% confidenceFactExact time
In the 12GB VRAM configuration, Breeze TTS2 requires about 8.5GB of VRAM (weights plus runtime overhead) and must run entirely on the GPU, while the LLM portion takes about nearly 4GB at a 128K context.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/29/2026
First Seen
Valid until: 1/27/2027
Sources
Related Entities
Related Claims
UnverifiedThe KV cache overhead per token for Llama 3.1 8B is approximately 128 KB.78% similarUnverifiedOn an 8GB VRAM GPU, this user runs stably at a 32k context; pushing to a 42k context left only about 130MB of headroom before VRAM crash, and 64k was not possible.78% similarUnverifiedTTM 模型参数量仅约 0.8M（百万级），文件大小约三兆字节，无需 GPU，在普通 CPU 上就能运行75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1112080API
curl https://kongchang.com/api/v1/knowledge/claims/1112080MCP
get_claim(id=1112080)