Interfaze

logo

Beta

pricing

docs

blog

sign in

Qwen3.5 35B A3B Uncensored HauhauCS Aggressive

Qwen3.5 35B A3B Uncensored HauhauCS Aggressive by HauhauCS, a image-text-to-text model with multimodal capabilities. Understand and compare multimodal features, benchmarks, and capabilities.

Comparison

FeatureQwen3.5 35B A3B Uncensored HauhauCS AggressiveInterfaze
Input Modalities

text, image, video

image, text, audio, video, document

Native OCRNoYes
Long Document ProcessingNoYes
Language Support

201 partial

162+

Native Speech-to-TextNoYes
Native Object DetectionNoYes
Guardrail ControlsNoYes
Context Input Size

262K

1M

Tool CallingNo

Tool calling supported + built in browser, code execution and web search

Scaling

FeatureQwen3.5 35B A3B Uncensored HauhauCS AggressiveInterfaze
Scaling

Self-hosted/Provider-hosted with quantization

Unlimited

View model card on Hugging Face

Join the Discord for updates, roadmaps, projects, or just to chat.

Qwen3.5-35B-A3B uncensored by HauhauCS. 0/465 refusals.

About

No changes to datasets or capabilities. Fully functional, 100% of what the original authors intended - just without the refusals.

These are meant to be the best lossless uncensored models out there.

Aggressive Variant

Stronger uncensoring — model is fully unlocked and won't refuse prompts. May occasionally append short disclaimers (baked into base model training, not refusals) but full content is always generated.

For a more conservative uncensor that keeps some safety guardrails, check the Balanced variant when it's available.

Downloads

FileQuantSize
Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-BF16.ggufBF1665 GB
Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q8_0.ggufQ8_035 GB
Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q6_K.ggufQ6_K27 GB
Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q5_K_M.ggufQ5_K_M24 GB
Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M.ggufQ4_K_M20 GB
Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ4_XS.ggufIQ4_XS18 GB
Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q3_K_M.ggufQ3_K_M16 GB
Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ3_M.ggufIQ3_M15 GB
Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ2_M.ggufIQ2_M11 GB
mmproj-Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.ggufmmproj (f16)858 MB

All quants generated with importance matrix (imatrix) for optimal quality preservation on abliterated weights.

Specs

  • 35B total parameters, ~3B active per forward pass (MoE)
  • 256 experts, 8 routed + 1 shared per token
  • Hybrid architecture: Gated DeltaNet linear attention + full softmax attention (3:1 ratio)
  • 40 layers, pattern: 10 x (3 x DeltaNet-MoE + 1 x Attention-MoE)
  • 262K native context (extendable to 1M with YaRN)
  • Natively multimodal (text, image, video)
  • Multi-token prediction (MTP) support
  • 248K vocabulary, 201 languages
  • Based on Qwen/Qwen3.5-35B-A3B

From the official Qwen authors:

Thinking mode (default):

  • General: temperature=1.0, top_p=0.95, top_k=20, min_p=0, presence_penalty=1.5
  • Coding/precise tasks: temperature=0.6, top_p=0.95, top_k=20, min_p=0, presence_penalty=0

Non-thinking mode:

  • General: temperature=0.7, top_p=0.8, top_k=20, min_p=0, presence_penalty=1.5
  • Reasoning tasks: temperature=1.0, top_p=1.0, top_k=40, min_p=0, presence_penalty=2.0

Important:

  • Keep at least 128K context to preserve thinking capabilities
  • Use --jinja flag with llama.cpp for proper chat template handling
  • Vision support requires the mmproj file alongside the main GGUF

Usage

Works with llama.cpp, LM Studio, Jan, koboldcpp, and other GGUF-compatible runtimes.


llama-cli -m Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf \
  --jinja -c 131072 -ngl 99


llama-cli -m Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf \
  --mmproj mmproj-Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.gguf \
  --jinja -c 131072 -ngl 99

Note: LM Studio may show 256x2.6B in the params column instead of 35B-A3B — this is a cosmetic metadata quirk, the model runs correctly.

Other Formats

  • GGUF (this repo)
  • GPTQ — coming soon

Other Models

Want more deterministic results?