GGUF quantizations of 0xA50C1A1/Muse-Glimmer-30B-abliterix.
[!Warning] As of September 13, 2026, this NVFP4 GGUF may not work out of the box in llama.cpp. Track issue: https://github.com/ggml-org/llama.cpp/issues/27178
[!Note] lm_head and embeddings are kept in Q8_0 instead of BF16 to reduce VRAM usage.