Qwen3 VL REAP 24B A3B needs about 15.5 GB of memory at Q4_K_M (a 14.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 11 quants, from 8.6 GB (Q2_K) to 24.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Qwen3 VL REAP 24B A3B – a vision‑language MoE model with 3B active parameters
Qwen3 VL REAP 24B A3B is a decoder‑only transformer with MoE MLP experts and a vision encoder. It retains full vision‑language capability while pruning roughly 25% of experts, reducing total parameters to 24.3B. The model is released under Apache 2.0.
Good at
- Vision‑language tasks
- Sparse MoE inference
- Instruction following
Limits
- No vision support beyond original VL
- Requires 8k context for memory estimates
- Large VRAM needed for higher quants
Best for
- Image captioning
- Multimodal QA
- Vision‑guided text generation
Who it’s for. Developers and researchers needing a lightweight vision‑language model with MoE sparsity. Suitable for local deployment on GPUs with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 8.6 GB | 9.9 GB | Too big | Get file → | |
| Q3_K_S | 10.2 GB | 11.5 GB | Too big | Get file → | |
| Q3_K_M | 11.2 GB | 12.6 GB | Too big | Get file → | |
| Q3_K_L | 12.2 GB | 13.5 GB | Too big | Get file → | |
| IQ4_XS | 12.6 GB | 14.0 GB | Too big | Get file → | |
| Q4_K_S | 13.3 GB | 14.6 GB | Too big | Get file → | |
| Q4_K_M | 14.2 GB | 15.5 GB | Too big | Get file → | |
| Q5_K_S | 16.1 GB | 17.4 GB | Too big | Get file → | |
| Q5_K_M | 16.6 GB | 17.9 GB | Too big | Get file → | |
| Q6_K | 19.1 GB | 20.4 GB | Too big | Get file → | |
| Q8_0 | 24.8 GB | 26.1 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (8.62 GB file, ~9.9 GB memory). For 12 GB VRAM use Q4_K_S (13.33 GB file, ~14.6 GB memory). For 16 GB VRAM use Q5_K_S (16.09 GB file, ~17.4 GB memory). Estimates are approximate.
What GPU do you need for Qwen3 VL REAP 24B A3B?
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_S (10.2 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (14.2 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (19.1 GB file, about 20.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (24.8 GB file, about 26.1 GB in use).
Which Qwen3 VL REAP 24B A3B quant should you choose?
Q4_K_M is the usual starting point for Qwen3 VL REAP 24B A3B: it balances file size and quality well. Here it is a 14.2 GB file.
The Q8_0 file is 24.8 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 Q2_K at 8.6 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
Source
Frequently asked questions about Qwen3 VL REAP 24B A3B
How much VRAM does Qwen3 VL REAP 24B A3B need?
About 15.5 GB at Q4_K_M with an 8K context window. That is the 14.2 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 Qwen3 VL REAP 24B A3B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3 VL REAP 24B A3B GGUF?
It depends on the quant: Q2_K is 8.6 GB, Q3_K_S is 10.2 GB, Q3_K_M is 11.2 GB, Q3_K_L is 12.2 GB, IQ4_XS is 12.6 GB, Q4_K_S is 13.3 GB and 5 more.
What context length does Qwen3 VL REAP 24B A3B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.
Where can I download Qwen3 VL REAP 24B A3B GGUF?
The files are on Hugging Face in the mradermacher/Qwen3-VL-REAP-24B-A3B-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 Qwen3 VL REAP 24B A3B 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 Qwen3 VL REAP 24B A3B on 8 GB VRAM?
Use the Q2_K quant; it requires about 9.9 GB VRAM at 8k context, which is close to 8 GB but may need swap.
Does the model support vision tasks?
Yes, it retains full vision‑language functionality from the base Qwen3‑VL.
What license applies to this model?
The model is released under the Apache 2.0 license.