Downloads · 30 days
173
16% of all-time downloads
gemma-4-E2B-it-assistant-GGUF
ManniX-ITA/gemma-4-E2B-it-assistant-GGUF
gemma-4-E2B-it-assistant-GGUF is a image-text-to-text model from ManniX-ITA. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for gguf. The card lists the license as gemma.
MTP / speculative-decoding draft head for gemma-4-E2B-it, in the upstream llama.cpp gemma4-assistant GGUF data-plane format (arch gemma4-assistant, with nextn. (+ maskedembd where applicable) tensors and embeddingleng…
All-time downloads
1.1K
Public
Repo size
507 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf507 MB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- gguf
- License
- gemma
- Access
- Public
- Created
- Jun 30, 2026
- Updated
- Sep 16, 2026
- SHA
- 2af63113
Try a prompt
Base models
Model card
From the Hugging Face model README
Gemma-4 E2B IT Assistant — MTP draft head (llama.cpp gemma4-assistant format)
MTP / speculative-decoding draft head for gemma-4-E2B-it, in the upstream
llama.cpp gemma4-assistant GGUF data-plane format (arch gemma4-assistant, with
nextn.* (+ masked_embd_* where applicable) tensors and embedding_length_out).
Use it as the drafter for self-speculative decoding against the matching
gemma-4-E2B-it target:
--mtp-head gemma-4-E2B-it-assistant.Q8_0.gguf --spec-type draft-assistant -ngld 99
Quants: F16, Q8_0, Q5_K_M, Q4_K_M, Q4_K_S.
Adapted from AtomicChat/gemma-4-E2B-it-assistant-GGUF. Weights byte-identical to the source GGUFs — only the GGUF metadata/tensor names were rewritten to the upstream gemma4-assistant data-plane format. The Gemma license applies.
- Task
- Image-Text-to-Text
- Library
- gguf
- License
- gemma
- Languages
- en
- Created
- Jun 30, 2026
- Updated
- Sep 16, 2026