CL

claude opus uncensored

ClaudeGGUF by lazekkkkUpdated 2026-04-23
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant11.7 GB
Quick answer

claude opus uncensored 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 11 quants, from 11.7 GB (IQ2_M) to 43.6 GB (Q8_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

claude opus uncensored is a 34.7B-parameter Claude model in GGUF format, quantized by lazekkkk. Its trained context length is 256K tokens. The repository has 11 quant files, from 11.7 GB (IQ2_M) to 43.6 GB (Q8_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M11.7 GB 12.8 GB
Too big Get file →
Q2_K15.0 GB 16.2 GB
Too big Get file →
IQ3_M15.4 GB 16.6 GB
Too big Get file →
IQ4_XS18.7 GB 19.9 GB
Too big Get file →
Q3_K19.0 GB 20.2 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 →
Q4_K23.4 GB 24.6 GB
Too big Get file →
Q5_K28.0 GB 29.2 GB
Too big Get file →
Q6_K30.6 GB 31.8 GB
Too big Get file →
Q8_K43.6 GB 44.8 GB
Too big Get file →

What GPU do you need for claude opus uncensored?

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 IQ2_M (11.7 GB file, about 12.8 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 (30.6 GB file, about 31.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_K (43.6 GB file, about 44.8 GB in use).

Which claude opus uncensored quant should you choose?

Q4_K_M is the usual starting point for claude opus uncensored: it balances file size and quality well. Here it is a 21.2 GB file.

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)
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bylazekkkk
FamilyClaude
Downloads (HF)78
Last updated2026-04-23

Frequently asked questions about claude opus uncensored

How much VRAM does claude opus uncensored 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 claude opus uncensored 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 claude opus uncensored GGUF?

It depends on the quant: IQ2_M is 11.7 GB, Q2_K is 15.0 GB, IQ3_M is 15.4 GB, IQ4_XS is 18.7 GB, Q3_K is 19.0 GB, IQ4_NL is 19.8 GB and 5 more.

What context length does claude opus uncensored 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 claude opus uncensored GGUF?

The files are on Hugging Face in the lazekkkk/claude_opus_uncensored repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from lazekkkk

All by lazekkkk →

More Claude models

All Claude →

Other large models

All large models →