QW

Bahushruth Qwen3.6 35B A3B Abliterated v4

QwenGGUF by BahushruthUpdated 2026-07-03
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant11.7 GB
Quick answer

Bahushruth Qwen3.6 35B A3B Abliterated v4 needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 13 quants, from 11.7 GB (IQ2_M) to 69.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

35B Qwen model with abliteration for uncensored use

Bahushruth Qwen3.6 35B A3B Abliterated v4 is a 35 billion‑parameter MoE model with 3 billion active parameters. It removes refusal behavior via norm‑preserving orthogonalization. The model supports a 262,144‑token context window and is released under Apache‑2.0.

Good at

  • Uncensored text generation
  • Large context handling
  • MoE efficiency

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • Large VRAM needed for higher quants

Best for

  • Research on safety alignment
  • Exploring uncensored LLM behavior
  • Large‑scale text generation

Who it’s for. Researchers and developers interested in studying or building upon uncensored LLMs. The model is intended for academic and safety research, not for general consumer use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M11.7 GB 12.8 GB
Too big Get file →
Q2_K12.9 GB 14.1 GB
Too big Get file →
IQ3_XXS13.6 GB 14.8 GB
Too big Get file →
IQ3_M15.4 GB 16.6 GB
Too big Get file →
Q3_K_M16.8 GB 17.9 GB
Too big Get file →
IQ4_XS18.7 GB 19.9 GB
Too big Get file →
IQ4_NL19.8 GB 21.0 GB
Too big Get file →
Q4_K_M21.2 GB 22.3 GB
Too big Get file →
Q5_K_M24.7 GB 25.9 GB
Too big Get file →
Q6_K28.5 GB 29.7 GB
Too big Get file →
Q8_036.9 GB 38.1 GB
Too big Get file →
BF1669.4 GB 70.5 GB
Too big Get file →
BF1669.4 GB 70.5 GB
Too big Get file →

For 8 GB VRAM, use IQ2_M (11.66 GB) or Q2_K (12.94 GB). For 16 GB VRAM, Q4_K_M (21.17 GB) or Q5_K_M (24.73 GB) are suitable. Higher quants like Q8_0 (36.9 GB) require 32 GB or more. Memory estimates are approximate.

What GPU do you need for Bahushruth Qwen3.6 35B A3B Abliterated v4?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (13.6 GB file, about 14.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 29.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).

Which Bahushruth Qwen3.6 35B A3B Abliterated v4 quant should you choose?

Q4_K_M is the usual starting point for Bahushruth Qwen3.6 35B A3B Abliterated v4: it balances file size and quality well. Here it is a 21.2 GB file.

The Q8_0 file is 36.9 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ2_M at 11.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters34.7B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized byBahushruth
FamilyQwen
Licenseapache-2.0
Downloads (HF)19,147
Last updated2026-07-03

Frequently asked questions about Bahushruth Qwen3.6 35B A3B Abliterated v4

How much VRAM does Bahushruth Qwen3.6 35B A3B Abliterated v4 need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Bahushruth Qwen3.6 35B A3B Abliterated v4 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Bahushruth Qwen3.6 35B A3B Abliterated v4 GGUF?

It depends on the quant: IQ2_M is 11.7 GB, Q2_K is 12.9 GB, IQ3_XXS is 13.6 GB, IQ3_M is 15.4 GB, Q3_K_M is 16.8 GB, IQ4_XS is 18.7 GB and 7 more.

What context length does Bahushruth Qwen3.6 35B A3B Abliterated v4 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Bahushruth Qwen3.6 35B A3B Abliterated v4 GGUF?

The files are on Hugging Face in the Bahushruth/Qwen3.6-35B-A3B-abliterated-v4-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Bahushruth Qwen3.6 35B A3B Abliterated v4 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Use the IQ2_M or Q2_K quant, which are around 12 GB including memory overhead. 8 GB VRAM may be insufficient for full inference.

Does this model support vision?

No, the model has no vision capabilities.

What license applies?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from Bahushruth

All by Bahushruth →

More Qwen models

All Qwen →

Other large models

All large models →