Downloads · 30 days
659
10% of all-time downloads
deucebucket/Gemma-4-26B-A4B-it-Heretic-Cerebellum-GGUF
Gemma-4-26B-A4B-it-Heretic-Cerebellum-GGUF is a text generation model from deucebucket. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as gemma.
<p align="center" <img src="cerebellumbanner.png" alt="Cerebellum" width="640" </p
Downloads · 30 days
659
10% of all-time downloads
All-time downloads
6.8K
Public
Repo size
24.7 GB
Likes
8
Public
Click a slice to open those files.
.gguf24.7 GB · 100%
From the Hugging Face model README
Sensitivity-guided mixed-precision GGUF of coder3101/gemma-4-26B-A4B-it-heretic, a decensored variant of google/gemma-4-26B-A4B-it. It uses the Cerebellum v6 tensor allocation transferred verbatim onto the heretic weights. The shipped file carries Google's updated Gemma 4 chat-template metadata (2026-05-18 state) with zero tensor changes. Versions appear in filenames, not the repo name.
| File | Description |
|---|---|
gemma-4-26B-A4B-it-heretic-cerebellum-v1.1-templatefix-Q3_K_M.gguf | ~11 GB; v1 allocation + updated chat-template metadata |
gemma-4-26B-A4B-it-heretic.mmproj-f16.gguf | vision projector (required for image/video) |
Measured directly on the GGUF with llama.cpp llama-server on an RTX 3090,
temperature 0, project benchmark harness. The v1.1 templatefix file is metadata-only
over v1, so these describe the same weights. The comparison column is our own plain
(non-heretic) Cerebellum v6 build on the same harness, shown so the abliteration cost
is visible. Summary JSONs and per-question samples are in benchmark_results/.
| Benchmark | Heretic v6 alloc (11 GB) | Plain Cerebellum v6 (11 GB) |
|---|---|---|
| ARC-Challenge (1172 q) | 95.48% | 95.56% |
| HellaSwag (10042 q) | 83.49% | 84.55% |
| MMLU-Redux (2400 q) | 71.42% | 71.33% |
| HumanEval base (chat, no-think) | 92.07% | pending re-audit |
| HumanEval+ (chat, no-think) | 89.63% | pending re-audit |
| Vision smoke | 6/6 | — |
HumanEval/HumanEval+ used the chat-completions harness
(scripts/benchmark_evalplus_chat.py, enable_thinking: false,
thinking_budget_tokens: 0, BENCH_WORKERS=1, max_tokens: 768). The completion
audit for that run recorded 0 prompt echoes, 0 repeated function definitions,
0 pass-only outputs, and 2 genuine syntax failures. The plain v6 HumanEval artifacts
were raw-completions and are marked for re-audit, so no plain-v6 HumanEval is published.
Gemma 4 requires --jinja. For non-thinking output, pass request-level
chat_template_kwargs: {"enable_thinking": false} and thinking_budget_tokens: 0;
do not set a fixed server --reasoning-budget (it can burn output into hidden
reasoning until the length cap, which looks like a repetition loop).
llama-server \
--model gemma-4-26B-A4B-it-heretic-cerebellum-v1.1-templatefix-Q3_K_M.gguf \
--mmproj gemma-4-26B-A4B-it-heretic.mmproj-f16.gguf \
-ngl 99 --ctx-size 65536 --parallel 1 --flash-attn on \
--cache-type-k q8_0 --cache-type-v q8_0 --jinja --reasoning auto
Measured on one RTX 3090 (24 GB), KV q8_0: context to 131,072. This rig's measurements; no quality claims beyond them.
coder3101/gemma-4-26B-A4B-it-heretic