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

Mediform/gemma-4-E4B-it-assistant-gguf overview

gemma 4 E4B it assistant MTP draft — GGUF F16 F16 GGUF conversion of google/gemma 4 E4B it assistant — the stock MTP multi token prediction assistant head for …

ggufspeculative-decodingmtpgemma-4base_model:google/gemma-4-E4B-it-assistantbase_model:quantized:google/gemma-4-E4B-it-assistantlicense:gemmaendpoints_compatibleregion:us

Runs locally from ~94.1 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
Author

Repository Files & Downloads

1 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
gemma-4-E4B-it-assist-F16.ggufGGUFF1694.1 MBDownload

Model Details

Model IDMediform/gemma-4-E4B-it-assistant-gguf
AuthorMediform
Pipeline
Licensegemma
Base modelgoogle/gemma-4-E4B-it-assistant
Last modified2026-07-10T11:25:42.000Z

Model README

---

license: gemma

base_model: google/gemma-4-E4B-it-assistant

tags:

- gguf

- speculative-decoding

- mtp

- gemma-4

---

gemma-4-E4B-it assistant (MTP draft) — GGUF F16

F16 GGUF conversion of google/gemma-4-E4B-it-assistant — the stock

MTP (multi-token-prediction) assistant head for Gemma-4 E4B-it. Finetune

revision 65892304d4eb7762acc45257a327885f7535e584.

Purpose

Draft model for speculative decoding against the stock

google/gemma-4-E4B-it-qat-q4_0-gguf target (llama.cpp

--spec-type draft-mtp / ngram-mod,draft-mtp, or Scribion's in-process

LlamaCppGemmaEngine). The assistant reads the target's hidden states, so

draft/target pairing matters:

| target | draft | mean accepted len (measured) |

|---|---|---|

| stock QAT q4_0 | this model | ~2.9 / 3 |

| stock QAT q4_0 | Mediform/gemma4-e4b-v13-assistant-rollout-gguf | ~2.1 / 3 (mismatched) |

Use Mediform/gemma4-e4b-v13-assistant-rollout-gguf when the target is the

v13-plainlora finetune; use this model when the target is stock QAT.

Speculative decoding is lossless — a mismatched draft only costs speed

(~28 vs ~36-40 tok/s decode on M-series), never output quality.

Run Mediform/gemma-4-E4B-it-assistant-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