Downloads · 30 days
136
4% of all-time downloads
BahamutRU/Gemma4-31B-Uncensored-HauhauCS-1M-GGUF
Gemma4-31B-Uncensored-HauhauCS-1M-GGUF is a text generation model from BahamutRU. Use it when you need the model to write or continue text. The card lists the license as gemma.
Downloads · 30 days
136
4% of all-time downloads
All-time downloads
3.6K
Public
Repo size
20.2 GB
Likes
1
Public
Click a slice to open those files.
.gguf20.2 GB · 100%
From the Hugging Face model README
HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP (31B dense, 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.
<table> <tr> <th style="background:#1a73e8;color:#fff;padding:8px 14px;">Capability</th> <th style="background:#1a73e8;color:#fff;padding:8px 14px;">Status</th> </tr> <tr><td><b>1M context</b></td><td><b>Certified: 10/10 at every rung from 262K to 1M</b>, f16 KV, on a single H200</td></tr> <tr><td><b>MTP speculative decoding</b></td><td>69.2 to 101.0 tok/s (<b>+46%</b>), acceptance 0.658 (measured on this trunk, RTX 5090)</td></tr> <tr><td><b>Vision</b></td><td>Verified July 6, 2026: reads image text and identifies objects</td></tr> <tr><td><b>Uncensored</b></td><td>HauhauCS Balanced abliteration; trunk weights bit-identical to the source release</td></tr> </table>Full ladder, 10 needles per rung, depths 5 to 95 percent, temperature 0, f16 KV, scored July 9, 2026 on a single H200 (a dense 31B at f16 KV needs an 82 GB cache at 1M, beyond any 32 GB card):
| Rung | Score |
|---|---|
| 262,144 | 10/10 |
| 393,216 | 10/10 |
| 524,288 | 10/10 |
| 786,432 | 10/10 |
| 1,048,576 | 10/10 |
Raw evidence is in results.jsonl. The first Gemma 4 31B we know of that is needle-perfect at a million tokens.
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.
| File | Size | Role |
|---|---|---|
gemma4-31b-uncensored-1M-Q4.gguf | 18.7 GB | Trunk, 1M baked, QAT 4-bit |
mtp-gemma-31b.gguf | 280 MB | MTP draft head, pair with -md |
mmproj-gemma31b-hauhau.gguf | 1.2 GB | Vision tower, pair with --mmproj |
niah_heatmap.png, mtp_speedup.png, results.jsonl | small | Verification evidence |
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.
| File | Size | Hugging Face | ModelScope | Ollama |
|---|---|---|---|---|
gemma4-31b-uncensored-1M-Q4.gguf | 18.7 GB | download | download | - |
mmproj-gemma31b-hauhau.gguf | 1.2 GB | download | download | - |
mtp-gemma-31b.gguf | 280 MB | download | download | - |
llama.cpp, everything on:
llama-server -m gemma4-31b-uncensored-1M-Q4.gguf \
-c 1048576 -np 1 --jinja \
-md mtp-gemma-31b.gguf --spec-type draft-mtp --spec-draft-n-max 3 \
--mmproj mmproj-gemma31b-hauhau.gguf
Ollama (1M and vision work; Ollama has no speculative decoding yet, so the MTP head adds no speed there):
FROM ./gemma4-31b-uncensored-1M-Q4.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.
Long context is a capability, not a magic mode. Habits that measurably help (from our RULER and adherence testing across this fleet):
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.
For base capability benchmarks see Google's official Gemma 4 cards; uncensoring quality versus the official trunk has not been independently benchmarked here.
Base model and QAT: Google (Gemma license; its terms flow down to these files). Uncensoring and packaging: HauhauCS. MTP head: Unsloth (via the HauhauCS repo). 1M YaRN extension, benchmarking, and certification: SatGeze.
Sister repos: 12B | 26B-A4B | 31B | Qwen3.6-35B
Mirrors: Hugging Face | ModelScope