Gemma-4-26B-A4B Uncensored (NVFP4)
Gemma-4-26B-A4B Uncensored is a community version of Google's Gemma 4 26B A4B (TrevorJS, Apache 2.0) with refusal behaviour removed by abliteration across the dense path and all experts — no new training data. Its card shows refusals falling from 98 to about 1 in 100 on its main prompt set; capability retention is documented only indirectly, so compare it with the original before relying on it. We serve it on hardware we operate inside the EEA; prompts and completions are not stored.
model id: gemma4-26b-unc
from openai import OpenAI client = OpenAI( api_key="hb-...", base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create( model="gemma4-26b-unc", messages=[{"role": "user", "content": "Hello"}],)print(r.choices[0].message.content)
curl https://api.heabsy.com/v1/chat/completions \ -H "Authorization: Bearer $HEABSY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gemma4-26b-unc", "messages": [{"role": "user", "content": "Hello"}] }'
import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.HEABSY_API_KEY, baseURL: "https://api.heabsy.com/v1",}); const r = await client.chat.completions.create({ model: "gemma4-26b-unc", messages: [{ role: "user", content: "Hello" }],});console.log(r.choices[0].message.content);
Price list, updated 12 September 2026. No minimum spend, no subscription.
About the model
- Developer
- TrevorJS
- Released
- April 2026
- Licence
- Apache-2.0
- Architecture
- mixture of experts · 25.2B parameters, 3.8B active per token
- Based on
- Gemma 4 26B A4B
- Languages named by the developer
- English
Source: the developer's model card, as of 17 September 2026.
Gemma 4 31B or 26B A4B?
Both come from Google DeepMind under Apache 2.0, read images as well as text, support more than 35 languages out of the box and keep thinking off unless you enable it.
Gemma 4 31B is dense (30.7B parameters) and scores higher on the card: 85.2 % on MMLU Pro and 80.0 % on LiveCodeBench v6. Gemma 4 26B A4B is a mixture of experts with 3.8B of 25.2B parameters active, built for speed, at 82.6 % and 77.1 %. Gemma-4-26B-A4B Uncensored is a community build of the 26B with refusals removed.
Licence: what it means for your company
Apache-2.0. A permissive open-source licence: you may use, modify and sell products built on the model, including commercially; when you redistribute the weights, the licence and copyright notices go with them.
A summary of the licence, not legal advice.
Technical details
- Context window
- 256K tokens
- Max output
- 65,536 tokens
- Throughput limit
- 4M tok/min
- Tokenizer
- Gemma
- Streaming
- yes
- Open weights
- TrevorJS/gemma-4-26B-A4B-it-uncensored
- max_tokens
- 1 … 65536
- temperature
- 0 … 2
- top_p
- 0 … 1
- frequency_penalty
- -2 … 2
- presence_penalty
- -2 … 2
- stop
- array
- seed
- integer
This model runs on GPUs we run inside the European Economic Area. Prompts and completions are not written to our logs or durable storage, nothing is used for training, and request content is processed in the EEA. It is the model behind every measurement on the inference page — 176 tok/s per stream, sub-second first token, 91–97% prefix-cache hit on agentic workloads.
Questions about this model
›Where is Gemma-4-26B-A4B Uncensored computed?
Inside the European Economic Area, on hardware we operate. The catalog reports the processing region per model, so you can answer a supervisory authority without asking us.
›Does Gemma-4-26B-A4B Uncensored store prompts and completions?
No. This model runs with zero data retention: request content is not written to durable storage and nothing is used for training.
›How large is the Gemma-4-26B-A4B Uncensored context window?
256K tokens, with up to 65,536 tokens of output.
›What does Gemma-4-26B-A4B Uncensored cost?
$0.12 per million input tokens and $0.38 per million output tokens. No minimum spend and no subscription; the same price list covers the API and the invoice.
›Is there a throughput limit on Gemma-4-26B-A4B Uncensored?
Yes, 4M tokens per minute. Higher limits are a question of volume, not of principle.
›Which languages does Gemma-4-26B-A4B Uncensored support?
The developer names English. Languages not on that list may still work, but they are not claimed — test on your own material first.
›Under which licence is Gemma-4-26B-A4B Uncensored released?
Apache-2.0. A permissive open-source licence: you may use, modify and sell products built on the model, including commercially; when you redistribute the weights, the licence and copyright notices go with them.
Compare with similar models
| Model | Developer | Parameters | Context | Licence | Input / 1M |
|---|---|---|---|---|---|
| Gemma-4-26B-A4B Uncensored (NVFP4) | TrevorJS | 25.2B / 3.8B | 256K | Apache-2.0 | $0.12 |
| Qwen3.8 27B (NVFP4) | Qwen (Alibaba) | 27B | 256K | Apache-2.0 | $0.40 |
| Qwen3.8 27B Uncensored (NVFP4) | OrcaRouter | 27B | 512K | Apache-2.0 | $0.20 |
| Gemma 4 26B A4B | Google DeepMind | 25.2B / 3.8B | 256K | Apache-2.0 | $0.07 |
30 more models behind the same key and the same invoice.
Browse the catalog