gemma-4-E2B-it-RKLLM by Hanzo Huang: Open-Weight Model

Model Card

By Hanzo Huang, published under apache-2.0, revision 8c0f76365eb3.

Text generation on Rockchip RK3576 and RK3588, converted from google/gemma-4-E2B-it. The files currently published here are text-only. Image and audio inputs are not supported by this release. A separate multimodal release is being validated; these existing files remain available for compatibility. Use the files for your board’s exact SoC. w4a16 uses 4-bit weights and 16-bit activations; w4a16g128 adds a weight group size of 128. w8a8 uses 8-bit weights and activations. File size below is download size, not total runtime RAM. With Docker installed on a matching Rockchip board, this example starts the RK3576 w4a16g128 model and its API on port 8001: The image includes its model file. See…

Read Hanzo Huang's full model card

Text generation on Rockchip RK3576 and RK3588, converted from google/gemma-4-E2B-it.

The files currently published here are text-only. Image and audio inputs are not supported by this release. A separate multimodal release is being validated; these existing files remain available for compatibility.

Conversion toolkit: RKLLM Toolkit 1.3.0.
Inputs / output: text → text.
License: apache-2.0; the upstream model card describes its terms and intended use.

Choose your files

Use the files for your board’s exact SoC. w4a16 uses 4-bit weights and 16-bit activations; w4a16_g128 adds a weight group size of 128. w8a8 uses 8-bit weights and activations. File size below is download size, not total runtime RAM.

Board	Quantization	Size	Language model
RK3576	`w4a16_g128`	6.65 GiB	gemma-4-E2B-it_RK3576_w4a16_g128.rkllm
RK3576	`w8a8`	7.37 GiB	gemma-4-E2B-it_RK3576_w8a8.rkllm
RK3588	`w8a8`	7.31 GiB	gemma-4-E2B-it_RK3588_w8a8.rkllm

Run on your board

With Docker installed on a matching Rockchip board, this example starts the RK3576 w4a16_g128 model and its API on port 8001:

sudo docker run --rm -d --name rkllm \
  --privileged -v /dev:/dev -p 8001:8001 \
  ghcr.io/hanzo-huang/rkllm-docker/llm/gemma-4-e2b-it:rk3576-w4a16-g128

The image includes its model file. See rkllm-docker for API requests, other board variants, and configuration.

To download the files separately instead:

hf download HanzoHuang/gemma-4-E2B-it-RKLLM \
  RK3576/gemma-4-E2B-it_RK3576_w4a16_g128.rkllm \
  --local-dir ./models

These are native RKLLM/RKNN artifacts. Use a compatible RKLLM runtime and the model’s correct chat template when integrating them in another application.

Release notes

No per-variant board benchmark is published here. Quantized output may differ from the original model; check responses on your own workloads. Use the toolkit version listed above when checking runtime compatibility.

SHA-256 checksums

973008fd7ebed81e2a26dcf7dcc1c28fde631837e3e021c7f3007d6e82647165  RK3576/gemma-4-E2B-it_RK3576_w4a16_g128.rkllm
b7357c01fcd51c8f896f06ee3a3746bc233031abd04e2fa0cebb5908b1382a01  RK3576/gemma-4-E2B-it_RK3576_w8a8.rkllm
ae81d1e37eb54b40d2d366ef622a0c05acfb15537272e982efc1dfdd60557979  RK3588/gemma-4-E2B-it_RK3588_w8a8.rkllm

Credits

Original model: google/gemma-4-E2B-it. Conversion tools: Rockchip RKLLM.

Identity and Version

Repository: HanzoHuang/gemma-4-E2B-it-RKLLM
Publisher: Hanzo Huang
Task: Text generation
Modality: Text
Library: rkllm
Parameters: Not stated by the source
Languages: Not stated by the source
Revision: 8c0f76365eb3218f2115689ff018e5a5970e23e4
First published: 2026-08-12
Last updated: 2026-10-19

Files and Weights

6 files, 22.9 GB in total.

Configuration1 file · 21.0 KB

Documentation1 file · 3.1 KB

Other3 files · 22.9 GB

Repository1 file · 1.8 KB

Every file

File	Type	Size	SHA-256
gemma-4-E2B-it_data_quant.json	Configuration	21.0 KB	—
README.md	Documentation	3.1 KB	—
RK3576/gemma-4-E2B-it_RK3576_w4a16_g128.rkllm	Other	7.1 GB	973008fd7ebe
RK3576/gemma-4-E2B-it_RK3576_w8a8.rkllm	Other	7.9 GB	b7357c01fcd5
RK3588/gemma-4-E2B-it_RK3588_w8a8.rkllm	Other	7.8 GB	ae81d1e37eb5
.gitattributes	Repository	1.8 KB	—

License and Download

License: apache-2.0
Access: Open weights, no gate

Download from Hanzo Huang

Released by Hanzo Huang through its official repository on Hugging Face. Read the license.

Built From

Derived from google/gemma-4-E2B-it

Questions About gemma-4-E2B-it-RKLLM

Can I use gemma-4-E2B-it-RKLLM commercially?

Yes. gemma-4-E2B-it-RKLLM is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Text generation

opt-125m

AI at Meta

OPT was first introduced in Open Pre-trained Transformer Language Models and first released in metaseq's repository on May 3rd 2022 by Meta AI. Disclaimer: The team releasing OPT wrote an official model card, which is available in Appendix D of the paper. Content from this model card has been written by the Hugging Face team. To quote the first two paragraphs of the official paper OPT was predominantly pretrained with English text, but a small amount of non-English data is still present within the training corpus via CommonCrawl. The model was pretrained using a causal language modeling (CLM) objective. OPT belongs to the same family of decoder-only models like GPT-3. As such, it was…

Open weights other 2,048 tokens transformers

View model

Model · Text generation

Ornith-1.5-9B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

View model

Model · Text generation

Ornith-1.5-35B-A3B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

View model

Model · Text generation

Ternary-Bonsai-2-27B-gguf

Prism ML

Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) - \~5.9 GB language model (down from \~54 GB FP16) — full 27B-class reasoning on a standard laptop or a single GPU - 98.2% of FP16 intelligence retained: 84.78 average across 14 thinking-mode benchmarks — far above the conventional IQ2XXS build (72.59) at about 82% of its footprint, and within 0.4 points of UD-Q4KXL at three times the footprint - Retains thinking, reasoning, and agentic behavior deep in the sub-4-bit regime, where conventional low-bit representations collapse: math within half a point of full precision (96.57), coding level with the baseline (89.42), agentic tool calling at 74.92…

Open weights apache-2.0 llama.cpp

View model

Model · Text generation

Qwen3.8-27B-Uncensored-GGUF

Jonathan Coletti

Uncensored Qwen3.8-27B, published as GGUF quantizations with the multi token prediction (MTP) head retained and verified. Refusal behaviour has been substantially reduced, not eliminated. See Measured behaviour for the numbers. Capabilities, training data, and architecture are otherwise unchanged. - Refusal directions removed with Heretic, which co minimizes refusal count against KL divergence from the base model. No handwritten refusal removal code, no finetuning, no additional training data. - Abliteration runs at bf16 (no 4 bit quantization). the resulting LoRA is merged into the bf16 base, so the published weights are not a quantized round trip. - mtp. tensors are copied verbatim from…

Open weights apache-2.0 llama.cpp

View model

Model · Text generation

Ornith-1.0-9B-GGUF

Ornith

Aloha! Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding. This model card documents Ornith-1.0-9B, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment. Ornith-1.0-9B is a dense ~9B model (≈19 GB in bf16), so it serves comfortably on a single 80GB GPU. The recipes below stand up an OpenAI-compatible server; add --tensor-parallel-size / --tp if you want to shard across more GPUs. For a quick local test (or to script offline generation), load the model directly with Transformers. Make sure you have a recent release installed — see the Transformers installation guide; Ornith-1.0-9B requires…

Open weights mit transformers

View model