ProCreations/grug-35b-mtp-gguf overview
grug 35b mtp gguf grug rock WITH prediction head inside. Q8 0 / Q5 K M / Q4 K M, mtp tensors included for llama.cpp speculative decoding needs build with qwen3…
Runs locally from ~857.6 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | ProCreations/grug-35b-mtp-gguf |
|---|---|
| Author | ProCreations |
| Pipeline | — |
| License | apache-2.0 |
| Base model | ProCreations/grug-35b-mtp |
| Last modified | 2026-07-24T20:24:13.000Z |
Model README
---
license: apache-2.0
base_model: ProCreations/grug-35b-mtp
tags: [grug, mtp, gguf, speculative-decoding]
language: [en]
---
grug-35b-mtp-gguf
grug rock WITH prediction head inside. Q8_0 / Q5_K_M / Q4_K_M, mtp tensors
included for llama.cpp speculative decoding (needs build with qwen3_5 MTP
support). draft head trained on grug data: t+2 agreement 68.1% (from-scratch head, experimental).
eye rock
caveman ask why grug blind. grug find eye.
download mmproj-grug-35b-mtp-f16.gguf beside any brain rock, then:
llama-server -m grug-35b-mtp-Q4_K_M.gguf \
--mmproj mmproj-grug-35b-mtp-f16.ggufeye rock same vision projector as v2.1 parent. MTP graft only touch prediction
head; vision tower unchanged. need recent llama.cpp with qwen3_5_moe + MTP
support.
main card: grug-35b-mtp.
no-MTP rocks: grug-35b-v2-gguf.
grug made by ProCreations.
Run ProCreations/grug-35b-mtp-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models