---

license: apache-2.0

base_model: aimeri/spoomplesmaxx-mockingbird-36B

library_name: gguf

pipeline_tag: text-generation

tags:

- roleplay

- creative-writing

language:

- en

---

spoomplesmaxx-mockingbird-36B — i1-GGUF (weighted/imatrix)

Weighted/imatrix GGUF quants of

spoomplesmaxx-mockingbird-36B.

The importance matrix was computed on a stratified sample of the model's

own training corpus — all ten lanes, rendered in the exact chat template

the model serves with — not a generic calibration set. At 3–4 bit these

should beat the static quants

noticeably; at Q5 the difference fades.

| Quant | Size | Notes |

|---|---|---|

| i1-IQ3_XXS | ~14 GB | smallest usable; VRAM-desperate only |

| i1-Q3_K_M | ~18 GB | the 18GB target, imatrix-weighted |

| i1-IQ4_XS | ~19 GB | best size/quality trade below Q4_K_M |

| i1-Q4_K_M | ~22 GB | recommended |

| i1-Q5_K_M | ~26 GB | closest to bf16 behavior |

The seed-native chat template is embedded in the GGUF metadata.

Sampling — read this part

temperature 1.0 · top_p 0.9 · repeat_penalty 1.0 (OFF)

> ⚠ Never use repetition, presence, or frequency penalties.

> The template ends every message with <seed:eos>; context-wide penalties

> suppress that token, the model stops ending its turns, and generation

> degenerates into the base model's untrained Chinese vocabulary. Many

> frontend presets default repeat_penalty to 1.05–1.1 — set it back to 1.0.

> Use DRY or XTC if you want extra anti-repetition; both leave special

> tokens alone.

Usable temperature window is ~0.95–1.05: lower loops verbatim, higher frays.

Full details on the

main model card.

mimids 01 · Apache 2.0