Qwen2.5 1.5B MoE A0.9B needs about 1.9 GB of memory at Q4_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.2 GB (Q4_K_M) to 3.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.
Qwen2.5 1.5B MoE A0.9B – Mixture‑of‑Experts model with ~0.85B active parameters
Qwen2.5-1.5B-MoE-A0.9B is a 1.78B parameter model with 0.9B active parameters per token. It was trained on 131072 context tokens and supports tool usage. The model is not instruction‑tuned and runs in stock llama.cpp and compatible builds.
Good at
- Fast inference on GPU
- Fast inference on CPU
- Tool usage
Limits
- No instruction tuning
- No vision support
- Requires llama.cpp or compatible
Best for
- Rapid prototyping of MoE models
- CPU‑bound inference
- Tool‑enabled applications
Who it’s for. Developers building custom LLMs who need a lightweight MoE model. The model is ideal for those who want faster inference with a smaller memory footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.2 GB | 1.9 GB | Fits | Get file → | |
| BF16 | 3.6 GB | 4.3 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K_M quant file (1.18 GB, ~1.9 GB memory at 8k context). If more precision is needed and 4 GB VRAM is available, use the BF16 quant file (3.57 GB, ~4.3 GB memory at 8k context).
What GPU do you need for Qwen2.5 1.5B MoE A0.9B?
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 Q4_K_M (1.2 GB file, about 1.9 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (3.6 GB file, about 4.3 GB in use).
Which Qwen2.5 1.5B MoE A0.9B quant should you choose?
Q4_K_M is the usual starting point for Qwen2.5 1.5B MoE A0.9B: it balances file size and quality well. Here it is a 1.2 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen2.5 1.5B MoE A0.9B
How much VRAM does Qwen2.5 1.5B MoE A0.9B need?
About 1.9 GB at Q4_K_M with an 8K context window. That is the 1.2 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 Qwen2.5 1.5B MoE A0.9B on an 8 GB GPU?
Yes, with BF16: the 3.6 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen2.5 1.5B MoE A0.9B GGUF?
It depends on the quant: Q4_K_M is 1.2 GB, BF16 is 3.6 GB.
What context length does Qwen2.5 1.5B MoE A0.9B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.
Where can I download Qwen2.5 1.5B MoE A0.9B GGUF?
The files are on Hugging Face in the bayliner1980/Qwen2.5-1.5B-MoE-A0.9B-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 Qwen2.5 1.5B MoE A0.9B use?
Hugging Face lists the license as apache-2.0. 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 Qwen2.5-1.5B-MoE-A0.9B on 8 GB VRAM?
Yes, the Q4_K_M quant file uses about 1.9 GB of VRAM at 8k context, well within an 8 GB budget.
Does it support vision?
No, the model does not have vision capabilities.
Is it instruction tuned?
No, it is a base completion model and is not instruction tuned.