GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

aimeri/spoomplesmaxx-thrasher-24B-GGUF overview

spoomplesmaxx thrasher 24B — GGUF static Static GGUF quants of spoomplesmaxx thrasher 24B https://huggingface.co/aimeri/spoomplesmaxx thrasher 24B "Thrash Meta…

ggufroleplaycreative-writingchatmltext-generationenbase_model:aimeri/spoomplesmaxx-thrasher-24Bbase_model:quantized:aimeri/spoomplesmaxx-thrasher-24Blicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~10.69 GB disk (12 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
text-generation
Author

Repository Files & Downloads

3 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
spoomplesmaxx-thrasher-24B.Q3_K_M.ggufGGUFGGUF10.69 GBDownload
spoomplesmaxx-thrasher-24B.Q4_K_M.ggufGGUFGGUF13.35 GBDownload
spoomplesmaxx-thrasher-24B.Q5_K_M.ggufGGUFGGUF15.61 GBDownload

Model Details

Model IDaimeri/spoomplesmaxx-thrasher-24B-GGUF
Authoraimeri
Pipelinetext-generation
Licenseapache-2.0
Base modelaimeri/spoomplesmaxx-thrasher-24B
Last modified2026-08-28T00:21:46.000Z

Model README

---

license: apache-2.0

base_model: aimeri/spoomplesmaxx-thrasher-24B

library_name: gguf

pipeline_tag: text-generation

tags:

- roleplay

- creative-writing

- chatml

language:

- en

---

spoomplesmaxx-thrasher-24B — GGUF (static)

Static GGUF quants of spoomplesmaxx-thrasher-24B

("Thrash Metal", mimids 02). ChatML template embedded — llama.cpp picks it up

without ceremony. See the main card for the full story: the token surgery

that put ChatML on a Mistral base, the checkpoint-selection battery, and the

measured sampler guidance.

spoomplesmaxx-thrasher-24B.Q5_K_M.gguf   ~16.8 GB   quality pick
spoomplesmaxx-thrasher-24B.Q4_K_M.gguf   ~14.3 GB   the 24GB-card sweet spot
spoomplesmaxx-thrasher-24B.Q3_K_M.gguf   ~11.5 GB   fits 12GB with room for ctx

Sampler (swept on the full-precision model): temperature 1.0 · min_p 0.05.

A mild repetition_penalty 1.05 eliminated the verbatim-loop tail in our

sweep at the cost of a rare unfinished turn — a reasonable opt-in here,

unlike on mockingbird. imatrix quants: coming in a separate repo — prefer

those at 3–4 bit once live.

For adults. Stays in character by design; bring your own moderation. Apache 2.0.

Run aimeri/spoomplesmaxx-thrasher-24B-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models