KI

Qwopus3.5 122B Distill Kimi Uncensored

KimiGGUF by morikomorizzUpdated 2026-06-23
Download on Hugging Face
Parameters125B
Context256K
Layers49
Architectureqwen35moe
Smallest quant59.1 GB
Quick answer

Qwopus3.5 122B Distill Kimi Uncensored needs about 68.5 GB of memory at IQ3_M (a 67.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 59.1 GB (IQ2_M) to 81.7 GB (IQ4_NL). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.

Qwopus3.5 122B Distill Kimi Uncensored – a large multimodal LLM

Qwopus3.5 122B Distill Kimi Uncensored is a 125 billion‑parameter Mixture of Experts model based on the Qwen3.5‑122B‑A10B architecture. It includes vision, text, and tool‑use capabilities and is released under the MIT license.

Good at

  • Reasoning and problem solving
  • Tool usage and API calls
  • Multimodal image‑to‑text tasks

Limits

  • Requires large VRAM – 60.4 GB at 8 k context for IQ2_M
  • No built‑in speedup from MTP head
  • No explicit language support list

Best for

  • Research on multimodal reasoning
  • Building AI assistants with tool integration
  • Evaluating vision‑to‑text pipelines

Who it’s for. Researchers and developers who need a large, uncensored multimodal model with reasoning and tool‑use abilities. The model is suitable for experimentation and prototyping rather than production deployment due to its high memory demands.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M59.1 GB 60.4 GB
Too big Get file →
IQ3_M67.2 GB 68.5 GB
Too big Get file →
IQ4_NL81.7 GB 83.0 GB
Too big Get file →

For a 8 GB VRAM system, none of the available quantizations fit. The smallest file, IQ2_M, requires 60.4 GB of VRAM at 8 k context. If you have 64 GB VRAM, IQ2_M is the most memory‑efficient choice. For 80 GB VRAM, IQ3_M or IQ4_NL can be used, but they require 68.5 GB and 83 GB respectively.

What GPU do you need for Qwopus3.5 122B Distill Kimi 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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Qwopus3.5 122B Distill Kimi Uncensored quant should you choose?

IQ3_M (67.2 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ2_M at 59.1 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
Parameters125B (approximate, mixture of experts)
Layers49
Trained context262,144 tokens
KV cache (fp16)98 KB per token

Frequently asked questions about Qwopus3.5 122B Distill Kimi Uncensored

How much VRAM does Qwopus3.5 122B Distill Kimi Uncensored need?

About 68.5 GB at IQ3_M with an 8K context window. That is the 67.2 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 Qwopus3.5 122B Distill Kimi Uncensored on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 60.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwopus3.5 122B Distill Kimi Uncensored GGUF?

It depends on the quant: IQ2_M is 59.1 GB, IQ3_M is 67.2 GB, IQ4_NL is 81.7 GB.

What context length does Qwopus3.5 122B Distill Kimi 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 0.8 GB at 8K and 3.3 GB at 32K.

Where can I download Qwopus3.5 122B Distill Kimi Uncensored GGUF?

The files are on Hugging Face in the morikomorizz/Qwopus3.5-122B-Distill-Kimi-Uncensored-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 Qwopus3.5 122B Distill Kimi Uncensored 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?

No. The smallest quantization requires 60.4 GB of VRAM at 8 k context, which exceeds 8 GB.

Does the model support vision tasks?

Yes. The vision tower is intact and works for image and video to text conversion.

Is the model licensed for commercial use?

The model is released under the MIT license, allowing commercial use.

Other GGUFs of Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated

Similar models

Browse all →

More from morikomorizz

All by morikomorizz →

More Kimi models

All Kimi →

Other large models

All large models →