[enhancement]: Anima GGUF transformers #9729

Is there an existing issue for this?

• I have searched the existing issues

What should this feature add?

Load community GGUF builds of the Anima transformer. Anima loads as bf16, scaled fp8, int8 and MXFP8 single files,
but there is no GGUF config, so a .gguf Anima file does not install as Anima.

Alternatives

Use the fp8 or int8 single file.

Additional Content

• Demand: Bedovyy/Anima-GGUF, Abiray/Anima-base-v1.0-GGUF, vanes430/Anima-Turbo-V1.1-GGUF.
• Both variants (Anima 2.9B with Qwen3 0.6B, Anima 3.8B with Qwen3.5) need to be recognised.
• The pattern from feat(ideogram4): load community GGUF transformers #9708 (Ideogram 4 GGUF) and feat(ernie-image): load GGUF transformers #9725 (ERNIE-Image GGUF) applies: a Main_GGUF_*_Config fingerprinted by keys (GGUF headers often name another architecture), a loader that keeps quantized Linears packed and unpacks the rest with unpack_ggml_at_load, and the denoise node's peak_dequant_transient_bytes, which already counts GGUF layers (fix(model-cache): reserve the GGUF dequantization transient in every node #9709).

The full matrix of what loads today is in #9726 (Model Format Support page).