This is a variant of
moonshotai/Kimi-K3
quantized with FP8_BLOCK quantization applied to MLP and experts layers. Attention layers were not quantized due to shape mismatches, namely with
self_attn.b_proj.weight
Kimi-K3-FP8-BLOCK huggingface.co is an AI model on huggingface.co that provides Kimi-K3-FP8-BLOCK's model effect (), which can be used instantly with this RedHatAI Kimi-K3-FP8-BLOCK model. huggingface.co supports a free trial of the Kimi-K3-FP8-BLOCK model, and also provides paid use of the Kimi-K3-FP8-BLOCK. Support call Kimi-K3-FP8-BLOCK model through api, including Node.js, Python, http.
Kimi-K3-FP8-BLOCK huggingface.co is an online trial and call api platform, which integrates Kimi-K3-FP8-BLOCK's modeling effects, including api services, and provides a free online trial of Kimi-K3-FP8-BLOCK, you can try Kimi-K3-FP8-BLOCK online for free by clicking the link below.
RedHatAI Kimi-K3-FP8-BLOCK online free url in huggingface.co:
Kimi-K3-FP8-BLOCK is an open source model from GitHub that offers a free installation service, and any user can find Kimi-K3-FP8-BLOCK on GitHub to install. At the same time, huggingface.co provides the effect of Kimi-K3-FP8-BLOCK install, users can directly use Kimi-K3-FP8-BLOCK installed effect in huggingface.co for debugging and trial. It also supports api for free installation.