Skip to page content
SAVRN
Search Plan a project

Open-weight model · Image and text to text

qwen3.5-9b-uncensored-ninfer

by Ruwwww ruwwww/qwen3.5-9b-uncensored-ninfer

qwen3.5-9b-uncensored-ninfer is an open-weight model for image and text to text from Ruwwww, released under Apache License 2.0. Its published files total 4.0 KB.

This repository contains HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive (via GitMylo's verified safetensors release) converted to the native NInfer.ninfer artifact format.

Parameters—
Context—
Weights4.0 KB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By Ruwwww, published under apache-2.0, revision 79702c246670.

This repository contains HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive (via GitMylo's verified safetensors release) converted to the native NInfer.ninfer artifact format. The artifact is intended specifically for NInfer; it is not a raw Transformers checkpoint, Safetensors distribution, or GGUF file. The artifact embeds the complete Text, Vision, MTP (Multi-Token Prediction), proposal-head, tokenizer, chat-template, and generation resources.

Read Ruwwww's full model card

Qwen3.5-9B Uncensored (HauhauCS Aggressive) for NInfer

This repository contains HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive (via GitMylo's verified safetensors release) converted to the native NInfer .ninfer artifact format.

The artifact is intended specifically for NInfer; it is not a raw Transformers checkpoint, Safetensors distribution, or GGUF file.

Artifact

Field Value
Filename qwen3_5_9b_uncensored.ninfer
Size 6,514,051,328 bytes (6.07 GiB)
SHA-256 9f87bf2bc4318d5ea9b01a8e4c6aced1171cff5911c85b53e9bd14fc9cfc1446
NInfer model ID qwen3.5-9b
NInfer weights ID groupwise-int
NInfer target key qwen3_5_9b

The artifact embeds the complete Text, Vision, MTP (Multi-Token Prediction), proposal-head, tokenizer, chat-template, and generation resources.

Verify the downloaded artifact with:

printf '%s  %s\n' \
  '9f87bf2bc4318d5ea9b01a8e4c6aced1171cff5911c85b53e9bd14fc9cfc1446' \
  'qwen3_5_9b_uncensored.ninfer' | sha256sum --check

Model Details

  • Base Model: Qwen/Qwen3.5-9B modified by HauhauCS (Aggressive refusal ablation)
  • Architecture: Qwen3.5 hybrid Gated DeltaNet linear attention + full softmax attention (32 layers: 24 linear attention, 8 full attention at intervals of 4)
  • Quantization Scheme: Native NInfer Groupwise Integer (Q4G64_F16S / Q5G64_F16S / W8G32_F16S hybrid + BF16 norms/vision)
  • MTP: 1 layer Multi-Token Prediction supported
  • VRAM Footprint: ~5.28 GiB weights resident in GPU memory

Usage with NInfer

Interactive CLI

./build/apps/ninfer qwen3_5_9b_uncensored.ninfer \
  --prompt "<|im_start|>user\nExplain quantum entanglement concisely.<|im_end|>\n<|im_start|>assistant\n" \
  --max-new 256

HTTP Server (ninfer-serve)

./build/apps/ninfer-serve qwen3_5_9b_uncensored.ninfer \
  --host 0.0.0.0 --port 8080 \
  --model-id qwen3.5-9b-uncensored \
  --device 0

Identity and Version

Repository
ruwwww/qwen3.5-9b-uncensored-ninfer
Publisher
Ruwwww
Task
Image and text to text
Modality
Image and text
Library
ninfer
Parameters
Not stated by the source
Languages
rtx-5060ti, rtx-5090
Revision
79702c246670ce385b5ef2ace010a07ca0572e9c
First published
2026-09-21
Last updated
2026-09-21

Files and Weights

2 files, 4.0 KB in total.

Documentation1 file · 2.5 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
README.mdDocumentation2.5 KB —
.gitattributesRepository1.5 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download from Ruwwww

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

Built From

Questions About qwen3.5-9b-uncensored-ninfer

Can I use qwen3.5-9b-uncensored-ninfer commercially?

Yes. qwen3.5-9b-uncensored-ninfer 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

Non-uniform GGUF quantizations of a 512-expert MoE, produced with GSQ and RCO, with a vision projector for multimodal use. This repository provides GGUF quantizations of Qwen3.8-Flash-Next at four sizes, together with the model's vision projector (mmproj) for multimodal use. In contrast to uniform quantization, which applies a single quantization type to all weight tensors, each model here assigns a separate quantization type to every tensor. The assignment is obtained by a gradient-based search that allocates precision according to per-tensor sensitivity, subject to a total size budget. The resulting files are standard GGUF and run unmodified in llama.cpp, Ollama, and LM Studio. A…

Open weights apache-2.0 gguf
View model

Model · Image and text to text

Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF

Michał Piszczek

I built this quant because the ready-made FP4 file answered the wrong question. It was fast, but on my short WikiText-2 control it scored 6.4949 PPL. Plain Q40 scored 6.3798. The first higher-quality hybrid went too far the other way: good perplexity, 34.19 tok/s, and no comfortable room for 256K plus vision. This is the build that survived both gates. It is a 17.1 GB, 5.01 BPW mixed-precision GGUF of Qwen/Qwen3.8-27B. It keeps large, tolerant matrices in native NVFP4 and spends more bits on selected attention, Gated DeltaNet, and late FFN tensors. The trained MTP layer remains embedded in the same GGUF. This is not a fine-tune. I built the private calibration workload from 5,472 messages…

Open weights apache-2.0
View model

Model · Image and text to text

Huihui-Qwen3.8-27B-abliterated-GGUF

Huihui.ai

This is an uncensored version of Qwen/Qwen3.8-27B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. The newly added Huihui-Qwen3.8-27B-abliterated-Underdog-Saluki series come from ConwayResearch/Underdog-Saluki-27B-1.0 and ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF. Only layers 22 to 52 (0-based indexing) have been ablated, while the other layers remain unablated. It may come with a small disclaimer warning. Due to ConwayResearch/Underdog-Saluki-27B-1.0 not providing an imatrix file, we will attempt to perform ablation by mixing the GGUF…

Open weights apache-2.0 transformers
View model

Qwen3.8-27B uncensored by HauhauCS 0/465 Refusals. This is the Aggressive variant: direct answers, no refusal behavior, and minimal preamble on hard prompts. Every text GGUF preserves Qwen3.8's native NextN head, and this release adds HauhauCS FastMTP: a specific acceleration sidecar qualified across the complete quant lineup at maximum native context. Vision is included through the separate BF16 projector. No changes to datasets or intended capabilities. This release preserves Qwen3.8-27B's text, reasoning, agentic, image, and video capabilities while applying the HauhauCS Aggressive uncensoring profile. Pick Aggressive when you specifically want the model to get to the answer without…

Open weights apache-2.0
View model

Model · Image and text to text

Qwen3.8-27B-GGUF

GGML Org

Run with https://llama.app - https://huggingface.co/Qwen/Qwen3.8-27B - https://huggingface.co/incoai/Qwen3.8-27B-DFlash2 - add info

Open weights apache-2.0
View model

Model · Image and text to text

Tiel-Coder-35B-A3B-GGUF-MTP

Saga

Tiel is the fast coder of the arsenal. At 4-bit quantization and 23 GB it fixes real codebase issues at the rate (and speed, with the right GPU) of Opus 4.6 medium, while holding the best multi-turn conversation of any local model we have measured. It is also cheerfully bad at trivia. Pick it for work. Pick something else for exams. Where it sits against the other local builds Multi-turn conversation Reasoning and knowledge Where it stands. On 25 SWE-bench-Live problems Tiel fixes 12 — the same as Opus 4.6 (medium), four more than Ornith-1.5 itself, three more than Nail, and four more than Sonnet 5 (medium). Among models of its own class it is first; the ones ahead are dense 27Bs and Opus…

Open weights mit gguf
View model