APUS Reflex 35B A3B needs about 22.9 GB of memory at Q4_K_M (a 21.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 13.2 GB (Q2_K) to 37.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
APUS Reflex 35B A3B – a 35.5B parameter Qwen3.5 MoE decision model
APUS Reflex 35B A3B is a 35.5B parameter Qwen3.5 MoE model designed for decision making, tool use, and vision tasks. It supports 262144 trained context tokens and is released under the apache-2.0 license.
Good at
- Decision making
- Tool use
- Vision support
Limits
- Requires large VRAM for full precision
- No native vision support in GGUF
- Mixture of experts limits single‑GPU usage
Best for
- Browser action selection
- Workflow step planning
- Natural‑language criteria evaluation
Who it’s for. Developers building assistant or agent systems that need a decision‑making backbone. The model is suitable for applications requiring reasoning, tool invocation, and vision integration within a single framework.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 13.2 GB | 14.4 GB | Too big | Get file → | |
| Q3_K_S | 15.5 GB | 16.7 GB | Too big | Get file → | |
| Q3_K_M | 17.2 GB | 18.4 GB | Too big | Get file → | |
| Q3_K_L | 18.6 GB | 19.7 GB | Too big | Get file → | |
| IQ4_XS | 19.4 GB | 20.6 GB | Too big | Get file → | |
| Q4_K_S | 20.4 GB | 21.6 GB | Too big | Get file → | |
| Q4_K_M | 21.7 GB | 22.9 GB | Too big | Get file → | |
| Q5_K_S | 24.6 GB | 25.8 GB | Too big | Get file → | |
| Q5_K_M | 25.3 GB | 26.5 GB | Too big | Get file → | |
| Q6_K | 29.2 GB | 30.4 GB | Too big | Get file → | |
| Q8_0 | 37.8 GB | 39.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (file size 13.25 GB, estimated memory 14.4 GB). For 16 GB VRAM, Q4_K_M (21.71 GB, 22.9 GB) or Q5_K_M (25.35 GB, 26.5 GB) are suitable. Larger GPUs can handle Q6_K or Q8_0 for higher precision.
What GPU do you need for APUS Reflex 35B 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: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q2_K (13.2 GB file, about 14.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (21.7 GB file, about 22.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (29.2 GB file, about 30.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (37.8 GB file, about 39.0 GB in use).
Which APUS Reflex 35B A3B quant should you choose?
Q4_K_M is the usual starting point for APUS Reflex 35B A3B: it balances file size and quality well. Here it is a 21.7 GB file.
The Q8_0 file is 37.8 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 13.2 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 APUS Reflex 35B A3B
How much VRAM does APUS Reflex 35B A3B need?
About 22.9 GB at Q4_K_M with an 8K context window. That is the 21.7 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 APUS Reflex 35B A3B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of APUS Reflex 35B A3B GGUF?
It depends on the quant: Q2_K is 13.2 GB, Q3_K_S is 15.5 GB, Q3_K_M is 17.2 GB, Q3_K_L is 18.6 GB, IQ4_XS is 19.4 GB, Q4_K_S is 20.4 GB and 5 more.
What context length does APUS Reflex 35B 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 0.7 GB at 8K and 2.8 GB at 32K.
Where can I download APUS Reflex 35B A3B GGUF?
The files are on Hugging Face in the mradermacher/APUS-Reflex-35B-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 APUS Reflex 35B 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 APUS Reflex 35B A3B on 8 GB VRAM?
Only the Q2_K quant is feasible on 8 GB VRAM, as it estimates 14.4 GB memory at 8k context.
Does the model support vision tasks?
Yes, the model has detected vision abilities, but the GGUF files do not include a vision tokenizer.
What license applies to this model?
The model is released under the apache-2.0 license.