Unverified50% confidenceReleaseExact time
AntAngelMed officially provides an FP8 version, and the community has a GGUF quantized version made by mradermacher that can be used with llama.cpp.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedOllama v0.40.4 upgrades llama.cpp to version b11521, committed by jmorganca, mainly aimed at support for decision models and EmbeddingGemma 2.65% similarUnverifiedThe llama.cpp inference framework does not natively support the FP8 format, and Q8_0 is not equivalent to FP861% similarUnverifiedPyTorch 2.0开始将ROCm后端纳入官方一级支持，vLLM在2024年完成对AMD GPU的适配57% similarUnverifiedllama.cpp 支持从 Q2 到 Q8 的多种量化格式56% similarUnverifiedWith the maturation of local inference frameworks such as llama.cpp and Ollama, and advances in quantization techniques (such as GGUF and AWQ), running models with 7B–13B parameter scales on consumer-grade hardware has become possible.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1032162API
curl https://kongchang.com/api/v1/knowledge/claims/1032162MCP
get_claim(id=1032162)