GI

GigaChat 20B A3B Instruct v1.5 Abliterated

GigachatGGUF by mradermacherUpdated 2025-06-28
Download on Hugging Face
Parameters20.6B
Context128K
Layers28
Architecturedeepseek
Smallest quant7.6 GB
Quick answer

GigaChat 20B A3B Instruct v1.5 Abliterated needs about 13.9 GB of memory at Q4_K_M (a 12.5 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 11 quants, from 7.6 GB (Q2_K) to 21.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

GigaChat 20B A3B Instruct v1.5 Abliterated is a 20.6B-parameter Gigachat model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 11 quant files, from 7.6 GB (Q2_K) to 21.9 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K7.6 GB 9.0 GB
Too big Get file →
Q3_K_S9.0 GB 10.4 GB
Too big Get file →
Q3_K_M9.9 GB 11.3 GB
Too big Get file →
Q3_K_L10.7 GB 12.1 GB
Too big Get file →
IQ4_XS11.1 GB 12.6 GB
Too big Get file →
Q4_K_S11.7 GB 13.2 GB
Too big Get file →
Q4_K_M12.5 GB 13.9 GB
Too big Get file →
Q5_K_S14.2 GB 15.6 GB
Too big Get file →
Q5_K_M14.6 GB 16.1 GB
Too big Get file →
Q6_K16.9 GB 18.3 GB
Too big Get file →
Q8_021.9 GB 23.3 GB
Too big Get file →

What GPU do you need for GigaChat 20B A3B Instruct v1.5 Abliterated?

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: the best quant that fits is Q3_K_M (9.9 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_S (14.2 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (21.9 GB file, about 23.3 GB in use).

Which GigaChat 20B A3B Instruct v1.5 Abliterated quant should you choose?

Q4_K_M is the usual starting point for GigaChat 20B A3B Instruct v1.5 Abliterated: it balances file size and quality well. Here it is a 12.5 GB file.

The Q8_0 file is 21.9 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 7.6 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

Architecturedeepseek
Parameters20.6B (approximate, mixture of experts)
Active parameters3B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Frequently asked questions about GigaChat 20B A3B Instruct v1.5 Abliterated

How much VRAM does GigaChat 20B A3B Instruct v1.5 Abliterated need?

About 13.9 GB at Q4_K_M with an 8K context window. That is the 12.5 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 GigaChat 20B A3B Instruct v1.5 Abliterated on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GigaChat 20B A3B Instruct v1.5 Abliterated GGUF?

It depends on the quant: Q2_K is 7.6 GB, Q3_K_S is 9.0 GB, Q3_K_M is 9.9 GB, Q3_K_L is 10.7 GB, IQ4_XS is 11.1 GB, Q4_K_S is 11.7 GB and 5 more.

What context length does GigaChat 20B A3B Instruct v1.5 Abliterated support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download GigaChat 20B A3B Instruct v1.5 Abliterated GGUF?

The files are on Hugging Face in the mradermacher/GigaChat-20B-A3B-instruct-v1.5-abliterated-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of GigaChat-20B-A3B-instruct-v1.5-abliterated

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gigachat models

All Gigachat →

Other medium models

All medium models →