---
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 — GGUF (static)

Static GGUF quants of
[spoomplesmaxx-mockingbird-36B](https://huggingface.co/aimeri/spoomplesmaxx-mockingbird-36B),
the first of the mimids. Weighted/imatrix quants (calibrated on the model's
own training corpus) live in
[-i1-GGUF](https://huggingface.co/aimeri/spoomplesmaxx-mockingbird-36B-i1-GGUF);
prefer those at 3–4 bit if your runtime supports them.

| Quant | Size | Notes |
|---|---|---|
| Q3_K_M | ~18 GB | the 18GB target; fine with a good card |
| Q4_K_S | ~21 GB | |
| Q4_K_M | ~22 GB | recommended balance |
| Q5_K_M | ~26 GB | closest to bf16 behavior |

The seed-native chat template is embedded in the GGUF metadata — llama.cpp,
koboldcpp, and LM Studio pick it up automatically.

## 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, corpus notes, and training story on the
[main model card](https://huggingface.co/aimeri/spoomplesmaxx-mockingbird-36B).

*mimids 01 · Apache 2.0*