DE

DeepSeek R1 0528 Qwen3 8B heretic

DeepSeekGGUF by richardyoungUpdated 2026-10-20
Download on Hugging Face
Parameters8.2B
Context128K
Layers36
Architectureqwen3
Smallest quant0.0 GB
Quick answer

DeepSeek R1 0528 Qwen3 8B heretic needs about 6.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 7 quants, from 0.0 GB to 8.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

DeepSeek R1 0528 Qwen3 8B heretic – a reasoning model with ablated safety refusals

DeepSeek R1 0528 Qwen3 8B heretic is an 8.2 billion‑parameter model based on Qwen3 architecture. It has been ablated to remove safety refusals while preserving reasoning chains. The model is released under the MIT license and supports up to 131072 context tokens.

Good at

  • Reasoning with chain generation
  • Unrestricted local inference
  • Research on alignment techniques

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • License is MIT – no commercial restrictions

Best for

  • Local reasoning tasks
  • Creative writing without safety filters
  • Educational alignment studies

Who it’s for. Researchers, developers, and writers who need a reasoning model that can comply with requests the original model would refuse. Use responsibly and in accordance with applicable laws.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.7 GB
Fits Get file →
IQ3_M3.9 GB 5.6 GB
Fits Get file →
IQ4_XS4.6 GB 6.3 GB
Fits Get file →
Q4_K_M5.0 GB 6.7 GB
Fits Get file →
Q5_K_M5.9 GB 7.6 GB
Tight Get file →
Q6_K6.7 GB 8.4 GB
Too big Get file →
Q8_08.7 GB 10.4 GB
Too big Get file →

For 8 GB VRAM, use IQ4_XS (file size 4.56 GB, memory 6.3 GB at 8 k context). For 12 GB VRAM, Q4_K_M (5.03 GB, 6.7 GB). For 16 GB VRAM, Q5_K_M (5.85 GB, 7.6 GB). Estimates are approximate.

What GPU do you need for DeepSeek R1 0528 Qwen3 8B heretic?

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: the best quant that fits is the main file (0.0 GB file, about 1.7 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ3_M (3.9 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).

Which DeepSeek R1 0528 Qwen3 8B heretic quant should you choose?

Q4_K_M is the usual starting point for DeepSeek R1 0528 Qwen3 8B heretic: it balances file size and quality well. Here it is a 5.0 GB file.

The Q8_0 file is 8.7 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters8.2B
Layers36
Trained context131,072 tokens
KV cache (fp16)144 KB per token

Source

Quantized byrichardyoung
FamilyDeepSeek
Licensemit
Downloads (HF)4,664
Last updated2026-10-20

Frequently asked questions about DeepSeek R1 0528 Qwen3 8B heretic

How much VRAM does DeepSeek R1 0528 Qwen3 8B heretic need?

About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 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 DeepSeek R1 0528 Qwen3 8B heretic on an 8 GB GPU?

Yes, with Q5_K_M: the 5.9 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of DeepSeek R1 0528 Qwen3 8B heretic GGUF?

It depends on the quant: file is 0.0 GB, IQ3_M is 3.9 GB, IQ4_XS is 4.6 GB, Q4_K_M is 5.0 GB, Q5_K_M is 5.9 GB, Q6_K is 6.7 GB and 1 more.

What context length does DeepSeek R1 0528 Qwen3 8B heretic support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download DeepSeek R1 0528 Qwen3 8B heretic GGUF?

The files are on Hugging Face in the richardyoung/DeepSeek-R1-0528-Qwen3-8B-heretic-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 DeepSeek R1 0528 Qwen3 8B heretic use?

Hugging Face lists the license as mit. 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?

Yes, the IQ4_XS quant uses about 6.3 GB at 8 k context, which fits in 8 GB VRAM with some headroom.

Does this model support vision?

No, the model has no vision capabilities.

What license does it use?

The model is released under the MIT license, inherited from the base model.

Other GGUFs of DeepSeek-R1-0528-Qwen3-8B-heretic

Similar models

Browse all →

More from richardyoung

All by richardyoung →

More DeepSeek models

All DeepSeek →

Other small models

All small models →