GigaChat3 10B A1.8B needs about 7.6 GB of memory at Q4_K_M (a 6.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 26 quants, from 0.0 GB to 21.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
GigaChat3 10B A1.8B – a 10B Mixture‑of‑Experts dialogue model
GigaChat3 10B A1.8B is a dialogue model from the Gigachat family. It uses a deepseek2 architecture with Multi‑head Latent Attention and Multi‑Token Prediction. The model has 10.7 billion total parameters and 1.8 billion active parameters.
Good at
- High inference throughput with MTP
- Efficient KV cache via MLA
- Large context of 262144 tokens
Limits
- Requires 8 k context for memory estimates
- No vision support
- MIT license limits commercial use to open‑source projects
Best for
- Fast chatbot inference on limited GPU
- Research on MoE architectures
- Deploying on edge devices with quantization
Who it’s for. Developers needing a high‑throughput dialogue model with a large context window. Researchers exploring MoE and efficient attention mechanisms. Teams deploying LLMs on GPUs with limited VRAM using quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.0 GB | Fits | Get file → | |
| IQ2_S | 3.3 GB | 4.3 GB | Fits | Get file → | |
| IQ2_M | 3.7 GB | 4.7 GB | Fits | Get file → | |
| Q2_K | 4.1 GB | 5.0 GB | Fits | Get file → | |
| Q2_K_L | 4.3 GB | 5.2 GB | Fits | Get file → | |
| IQ3_XXS | 4.5 GB | 5.5 GB | Fits | Get file → | |
| IQ3_XS | 4.7 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_S | 4.9 GB | 5.9 GB | Fits | Get file → | |
| IQ3_M | 5.1 GB | 6.1 GB | Fits | Get file → | |
| Q3_K_M | 5.1 GB | 6.1 GB | Fits | Get file → | |
| Q3_K_L | 5.3 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_XL | 5.4 GB | 6.4 GB | Fits | Get file → | |
| IQ4_XS | 5.9 GB | 6.9 GB | Fits | Get file → | |
| IQ4_NL | 6.2 GB | 7.2 GB | Fits | Get file → | |
| Q4_0 | 6.3 GB | 7.3 GB | Tight | Get file → | |
| Q4_K_S | 6.4 GB | 7.4 GB | Tight | Get file → | |
| Q4_K_M | 6.7 GB | 7.6 GB | Tight | Get file → | |
| Q4_K_L | 6.8 GB | 7.8 GB | Tight | Get file → | |
| Q4_1 | 6.8 GB | 7.8 GB | Tight | Get file → | |
| Q5_K_S | 7.5 GB | 8.4 GB | Too big | Get file → | |
| Q5_K_M | 7.7 GB | 8.7 GB | Too big | Get file → | |
| Q5_K_L | 7.8 GB | 8.8 GB | Too big | Get file → | |
| Q6_K | 8.8 GB | 9.8 GB | Too big | Get file → | |
| Q6_K_L | 8.9 GB | 9.9 GB | Too big | Get file → | |
| Q8_0 | 11.4 GB | 12.3 GB | Too big | Get file → | |
| BF16 | 21.4 GB | 22.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (6.66 GB file, ~7.6 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (7.71 GB file, ~8.7 GB memory) or Q6_K (8.84 GB file, ~9.8 GB memory). For 16 GB VRAM, Q8_0 (11.35 GB file, ~12.3 GB memory) offers the highest quality.
What GPU do you need for GigaChat3 10B A1.8B?
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 1.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q3_K_S (4.9 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_1 (6.8 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K_L (8.9 GB file, about 9.9 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 BF16 (21.4 GB file, about 22.3 GB in use).
Which GigaChat3 10B A1.8B quant should you choose?
Q4_K_M is the usual starting point for GigaChat3 10B A1.8B: it balances file size and quality well. Here it is a 6.7 GB file.
The Q8_0 file is 11.4 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
Source
Frequently asked questions about GigaChat3 10B A1.8B
How much VRAM does GigaChat3 10B A1.8B need?
About 7.6 GB at Q4_K_M with an 8K context window. That is the 6.7 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 10B A1.8B on an 8 GB GPU?
Yes, with Q4_1: the 6.8 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GigaChat3 10B A1.8B GGUF?
It depends on the quant: file is 0.0 GB, IQ2_S is 3.3 GB, IQ2_M is 3.7 GB, Q2_K is 4.1 GB, Q2_K_L is 4.3 GB, IQ3_XXS is 4.5 GB and 20 more.
What context length does GigaChat3 10B A1.8B 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 10B A1.8B GGUF?
The files are on Hugging Face in the bartowski/ai-sage_GigaChat3-10B-A1.8B-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 GigaChat3 10B A1.8B 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 GigaChat3 10B A1.8B on 8 GB VRAM?
Yes, with a Q4_K_M quantized file the estimated memory usage is about 7.6 GB at 8 k context, which fits within 8 GB VRAM.
Does this model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the MIT license.