Qwen1.5 MoE A2.7B Chat needs about 11.6 GB of memory at Q4_K_M (a 9.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 27 quants, from 4.6 GB (IQ1_S) to 15.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Qwen1.5 MoE A2.7B Chat – 14.3B total, 2.7B active parameters
Qwen1.5 MoE A2.7B Chat is a transformer‑based MoE decoder‑only language model. It contains 14.3B total parameters and activates 2.7B during inference. The model supports 32,768 token context and is available in multiple GGUF quantizations.
Good at
- High‑throughput inference with MoE
- Large context handling
- Efficient parameter usage
Limits
- No vision support
- Requires 8,000 token context for memory estimates
- License is other
Best for
- Chatbot backends
- Research prototyping
- Low‑resource inference
Who it’s for. Developers and researchers needing a large‑scale language model with reduced runtime parameters. Suitable for environments with limited GPU memory while maintaining strong performance.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 4.6 GB | 6.7 GB | Fits | Get file → | |
| IQ1_M | 4.8 GB | 6.9 GB | Fits | Get file → | |
| IQ2_XXS | 5.2 GB | 7.3 GB | Tight | Get file → | |
| IQ2_XS | 5.5 GB | 7.6 GB | Tight | Get file → | |
| IQ2_S | 5.5 GB | 7.6 GB | Tight | Get file → | |
| IQ2_M | 5.8 GB | 7.9 GB | Tight | Get file → | |
| Q2_K | 5.9 GB | 8.0 GB | Too big | Get file → | |
| Q2_K_S | 5.9 GB | 8.0 GB | Too big | Get file → | |
| IQ3_XXS | 6.3 GB | 8.5 GB | Too big | Get file → | |
| IQ3_XS | 6.5 GB | 8.6 GB | Too big | Get file → | |
| IQ3_S | 6.8 GB | 9.0 GB | Too big | Get file → | |
| Q3_K_S | 6.8 GB | 9.0 GB | Too big | Get file → | |
| IQ3_M | 6.9 GB | 9.0 GB | Too big | Get file → | |
| Q3_K_M | 7.4 GB | 9.5 GB | Too big | Get file → | |
| Q3_K_L | 7.7 GB | 9.9 GB | Too big | Get file → | |
| IQ4_XS | 7.8 GB | 10.0 GB | Too big | Get file → | |
| IQ4_NL | 8.1 GB | 10.3 GB | Too big | Get file → | |
| Q4_0 | 8.2 GB | 10.3 GB | Too big | Get file → | |
| Q4_K_S | 8.7 GB | 10.8 GB | Too big | Get file → | |
| Q4_1 | 9.0 GB | 11.1 GB | Too big | Get file → | |
| Q4_K_M | 9.5 GB | 11.6 GB | Too big | Get file → | |
| Q5_0 | 9.9 GB | 12.0 GB | Too big | Get file → | |
| Q5_K_S | 10.2 GB | 12.3 GB | Too big | Get file → | |
| Q5_1 | 10.8 GB | 12.9 GB | Too big | Get file → | |
| Q5_K_M | 10.8 GB | 12.9 GB | Too big | Get file → | |
| Q6_K | 12.8 GB | 14.9 GB | Too big | Get file → | |
| Q8_0 | 15.2 GB | 17.3 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (4.58 GB, 6.7 GB memory at 8k context). For 12 GB VRAM, IQ3_M (6.94 GB, 9 GB memory). For 24 GB VRAM, Q4_K_M (9.5 GB, 11.6 GB memory). Estimates are approximate.
What GPU do you need for Qwen1.5 MoE A2.7B Chat?
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: the best quant that fits is Q2_K_S (5.9 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_0 (9.9 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.8 GB file, about 14.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (15.2 GB file, about 17.3 GB in use).
Which Qwen1.5 MoE A2.7B Chat quant should you choose?
Q4_K_M is the usual starting point for Qwen1.5 MoE A2.7B Chat: it balances file size and quality well. Here it is a 9.5 GB file.
The Q8_0 file is 15.2 GB, about 1.6 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 IQ1_S at 4.6 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
Frequently asked questions about Qwen1.5 MoE A2.7B Chat
How much VRAM does Qwen1.5 MoE A2.7B Chat need?
About 11.6 GB at Q4_K_M with an 8K context window. That is the 9.5 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 Qwen1.5 MoE A2.7B Chat on an 8 GB GPU?
Yes, with Q2_K_S: the 5.9 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen1.5 MoE A2.7B Chat GGUF?
It depends on the quant: IQ1_S is 4.6 GB, IQ1_M is 4.8 GB, IQ2_XXS is 5.2 GB, IQ2_XS is 5.5 GB, IQ2_S is 5.5 GB, IQ2_M is 5.8 GB and 21 more.
What context length does Qwen1.5 MoE A2.7B Chat support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download Qwen1.5 MoE A2.7B Chat GGUF?
The files are on Hugging Face in the duyntnet/Qwen1.5-MoE-A2.7B-Chat-imatrix-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 Qwen1.5 MoE A2.7B Chat use?
Hugging Face lists the license as other. 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?
Yes, the IQ1_S quantization is 4.58 GB and requires about 6.7 GB of VRAM at 8k context.
Does this model support image inputs?
No, the model has no vision capabilities.
What inference clients can I use?
Supported clients include llama.cpp, KoboldCPP, ollama, text-generation-webui, GPT4All, and jan.