# Gemma4-26B-A4B Uncensored: 1M Context + MTP + Vision
[HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP](https://huggingface.co/HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP) (26B MoE, 4B active, Google QAT checkpoint) with a **1,048,576-token context baked in** (4x the native 262,144), shipping with its MTP speculative-decoding draft head and vision tower. All numbers below were measured on these exact files.
| Capability | Status |
|---|---|
| 1M context | ~91% mean recall across two seed sets (honesty note below) |
| MTP speculative decoding | 249.1 to 369.2 tok/s (+48%), acceptance 0.679 (measured on this trunk, RTX 5090) |
| Vision | Verified July 6, 2026: reads image text and identifies objects |
| Uncensored | HauhauCS Balanced abliteration; trunk weights bit-identical to the source release |
Full transparency: across two complete seed sets this trunk averages ~91 percent needle recall, dropping roughly one needle per rung at random depths, including inside the native 262K range. The official censored trunk scored 10/10 at 393K under the same harness, so this is a small flat abliteration tax, not a context-length failure. If a rare retrieval miss is unacceptable for your workload, use the [12B](https://huggingface.co/satgeze/Gemma4-12B-Uncensored-HauhauCS-1M-GGUF), which is certified clean. Every run, including the imperfect ones, is in `results.jsonl`. Rungs above 524K exceeded 32 GB VRAM and are being run on a 128 GB Mac; this card will update.
## MTP speculative decoding
The draft head predicts ahead and the trunk verifies every token, so output is identical to standard decoding, only faster. Measured speedup on this uncensored trunk beats the ~35 percent claimed upstream.
## Files
| File | Size | Role |
|---|---|---|
| `gemma4-26b-a4b-uncensored-1M-Q4_K_M.gguf` | 16.8 GB | Trunk, 1M baked, QAT 4-bit |
| `mtp-gemma-4-26B-A4B-it.gguf` | 252 MB | MTP draft head, pair with `-md` |
| `mmproj-gemma26b-hauhau.gguf` | 1.2 GB | Vision tower, pair with `--mmproj` |
| `niah_heatmap.png`, `mtp_speedup.png`, `results.jsonl` | small | Verification evidence |
## Every file, every mirror
Nothing was discontinued: every quant is one click away. Hugging Face carries the curated picks, ModelScope always carries everything, and Ollama serves ready-to-run tags.
On Ollama every tag ships with the vision tower bundled and the 1M rope metadata baked in.
| File | Size | Hugging Face | ModelScope | Ollama |
|---|---|---|---|---|
| `gemma4-26b-a4b-uncensored-1M-Q4_K_M.gguf` | 16.8 GB | [download](https://huggingface.co/satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF/resolve/main/gemma4-26b-a4b-uncensored-1M-Q4_K_M.gguf) | [download](https://www.modelscope.ai/models/satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF/resolve/master/gemma4-26b-a4b-uncensored-1M-Q4_K_M.gguf) | [`ollama run satgeze/gemma4-26b-uncensored-1m`](https://ollama.com/satgeze/gemma4-26b-uncensored-1m) |
| `mmproj-gemma26b-hauhau.gguf` | 1.2 GB | [download](https://huggingface.co/satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF/resolve/main/mmproj-gemma26b-hauhau.gguf) | [download](https://www.modelscope.ai/models/satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF/resolve/master/mmproj-gemma26b-hauhau.gguf) | bundled in every tag |
| `mtp-gemma-4-26B-A4B-it.gguf` | 252 MB | [download](https://huggingface.co/satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF/resolve/main/mtp-gemma-4-26B-A4B-it.gguf) | [download](https://www.modelscope.ai/models/satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF/resolve/master/mtp-gemma-4-26B-A4B-it.gguf) | - |
## Run it
llama.cpp, everything on:
```bash
llama-server -m gemma4-26b-a4b-uncensored-1M-Q4_K_M.gguf \
-c 1048576 -np 1 --jinja \
-md mtp-gemma-4-26B-A4B-it.gguf --spec-type draft-mtp --spec-draft-n-max 3 \
--mmproj mmproj-gemma26b-hauhau.gguf
```
Ollama (1M and vision work; Ollama has no speculative decoding yet, so the MTP head adds no speed there):
```
FROM ./gemma4-26b-a4b-uncensored-1M-Q4_K_M.gguf
RENDERER gemma4
PARSER gemma4
PARAMETER num_ctx 262144
```
The RENDERER and PARSER lines avoid imported-GGUF template bugs under tool-heavy use. Raise `num_ctx` as memory allows.
## How this was built
YaRN rope-scaling metadata (factor 4.0 over native 262,144) baked into the GGUF header with gguf-py; weights are bit-identical to the HauhauCS release, no fine-tuning. Gemma 4's dual-rope design takes YaRN on its global-attention layers. Certification harness: 10 needles per rung at depths 5 to 95 percent, temperature 0, seeded prompts, f16 KV only. Method and tooling: [github.com/satindergrewal/aviary-1m](https://github.com/satindergrewal/aviary-1m).
For base capability benchmarks see Google's official Gemma 4 cards; uncensoring quality versus the official trunk has not been independently benchmarked here.
## Credits
Base model and QAT: Google (Gemma license; its terms flow down to these files). Uncensoring and packaging: [HauhauCS](https://huggingface.co/HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP). MTP head: Unsloth (via the HauhauCS repo). 1M YaRN extension, benchmarking, and certification: [SatGeze](https://huggingface.co/satgeze).
Sister repos: [12B](https://huggingface.co/satgeze/Gemma4-12B-Uncensored-HauhauCS-1M-GGUF) | [26B-A4B](https://huggingface.co/satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF) | [31B](https://huggingface.co/satgeze/Gemma4-31B-Uncensored-HauhauCS-1M-GGUF) | [Qwen3.6-35B](https://huggingface.co/satgeze/Qwen3.6-35B-Uncensored-HauhauCS-1M-GGUF)
Mirrors: Hugging Face | [ModelScope](https://www.modelscope.ai/models/satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF)