GI

GigaChat3.1 Lightning Uncensored

GigachatGGUF by mradermacherUpdated 2026-03-30
Download on Hugging Face
Parameters10.7B
Context256K
Layers26
Architecturedeepseek2
Smallest quant4.0 GB
Quick answer

GigaChat3.1 Lightning Uncensored needs about 7.4 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 12 quants, from 4.0 GB (Q2_K) to 21.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

10.7B parameter GigaChat3.1 Lightning Uncensored in GGUF format

GigaChat3.1 Lightning Uncensored is a 10.7B parameter model based on deepseek2 architecture. It is a de‑aligned, creative writing model with no safety refusal vectors. The model supports tools and is available in multiple GGUF quantizations.

Good at

  • Creative writing
  • Gritty roleplay
  • Technical compliance

Limits

  • No vision support
  • License is MIT
  • No safety alignment

Best for

  • Unfiltered storytelling
  • Role‑play scenarios
  • Technical instruction

Who it’s for. Developers and writers who need an unfiltered, creative assistant. The model is suitable for projects that require detailed, descriptive text without safety constraints.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.0 GB 4.9 GB
Fits Get file →
Q3_K_S4.7 GB 5.6 GB
Fits Get file →
Q3_K_M5.1 GB 6.1 GB
Fits Get file →
Q3_K_L5.6 GB 6.5 GB
Fits Get file →
IQ4_XS5.8 GB 6.7 GB
Fits Get file →
Q4_K_S6.1 GB 7.1 GB
Fits Get file →
Q4_K_M6.5 GB 7.4 GB
Tight Get file →
Q5_K_S7.4 GB 8.3 GB
Too big Get file →
Q5_K_M7.6 GB 8.6 GB
Too big Get file →
Q6_K8.8 GB 9.7 GB
Too big Get file →
Q8_011.4 GB 12.3 GB
Too big Get file →
F1621.4 GB 22.3 GB
Too big Get file →

For 8 GB VRAM, use Q3_K_S (4.69 GB) or Q3_K_M (5.15 GB). If 12 GB VRAM is available, Q4_K_M (6.47 GB) or Q5_K_M (7.59 GB) provide better quality. Larger models like Q8_0 (11.35 GB) need 12.3 GB VRAM at 8 k context.

What GPU do you need for GigaChat3.1 Lightning 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: the best quant that fits is Q3_K_S (4.7 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (6.5 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.8 GB file, about 9.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.4 GB file, about 12.3 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (21.4 GB file, about 22.3 GB in use).

Which GigaChat3.1 Lightning Uncensored quant should you choose?

Q4_K_M is the usual starting point for GigaChat3.1 Lightning Uncensored: it balances file size and quality well. Here it is a 6.5 GB file.

The Q8_0 file is 11.4 GB, about 1.8 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 Q2_K at 4.0 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

Architecturedeepseek2
Parameters10.7B (approximate, mixture of experts)
Layers26
Trained context262,144 tokens
KV cache (fp16)55 KB per token

Source

Quantized bymradermacher
FamilyGigachat
Downloads (HF)754
Last updated2026-03-30

Frequently asked questions about GigaChat3.1 Lightning Uncensored

How much VRAM does GigaChat3.1 Lightning Uncensored need?

About 7.4 GB at Q4_K_M with an 8K context window. That is the 6.5 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 GigaChat3.1 Lightning Uncensored on an 8 GB GPU?

Yes, with Q4_K_M: the 6.5 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GigaChat3.1 Lightning Uncensored GGUF?

It depends on the quant: Q2_K is 4.0 GB, Q3_K_S is 4.7 GB, Q3_K_M is 5.1 GB, Q3_K_L is 5.6 GB, IQ4_XS is 5.8 GB, Q4_K_S is 6.1 GB and 6 more.

What context length does GigaChat3.1 Lightning 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 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download GigaChat3.1 Lightning Uncensored GGUF?

The files are on Hugging Face in the mradermacher/GigaChat3.1-Lightning-Uncensored-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, the Q3_K_S quant is 4.69 GB and requires about 5.6 GB VRAM at 8 k context. It is suitable for 8 GB VRAM setups.

Does this model support vision?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the MIT License.

Other GGUFs of GigaChat3.1-Lightning-Uncensored

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gigachat models

All Gigachat →

Other medium models

All medium models →