Downloads · 30 days
366
19% of all-time downloads
ProCreations/grug-v1.1-qwen-3.8-27b-mtp-gguf
grug-v1.1-qwen-3.8-27b-mtp-gguf is a text generation model from ProCreations. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
grug in box, with draft head still inside. same weight as ProCreations/grug-v1.1-qwen-3.8-27b-mtp.
Downloads · 30 days
366
19% of all-time downloads
All-time downloads
2K
Public
Repo size
138 GB
Likes
2
Public
Click a slice to open those files.
.gguf69.2 GB · 100%
From the Hugging Face model README
grug in box, with draft head still inside. same weight as ProCreations/grug-v1.1-qwen-3.8-27b-mtp.
normal grug GGUF throw the MTP head away (--no-mtp) because it just make file
bigger for nothing. this build keep it, as blk.64.nextn.* tensor, so engine
that do speculative decoding can guess ahead.
| file | size | vs no-mtp build |
|---|---|---|
grug-27b-v1.1-mtp-Q8_0.gguf | 29.0 GB | +0.4 GB |
grug-27b-v1.1-mtp-Q6_K.gguf | 22.4 GB | +0.3 GB |
grug-27b-v1.1-mtp-Q4_K_M.gguf | 16.8 GB | +0.3 GB |
mmproj-grug-27b-v1.1-mtp-f16.gguf | 0.9 GB | eyes, same |
the small extra size IS the draft head.
draft head only help when your engine actually use it. if your runtime ignore
nextn, you carry 0.3 GB for nothing — take the other repo.
Qwen3.8 native head agree with grug verifier 90.04% of time at t+2. grug retune it on grug own output and get 95.37% — disagree 1-in-21 instead of 1-in-10. higher agree = more draft token accepted = faster.
number is top-1 agreement with verifier, not measured wall-clock speedup. receipt and method on the MTP model card.
llama-cli -m grug-27b-v1.1-mtp-Q4_K_M.gguf -p "write a function that flattens a nested list"
verified output identical to non-MTP grug. draft head change speed, never answer.
quant load-tested with llama-bench before upload. use medium reasoning
effort — full table on the
main card.
apache-2.0.