35B A3B needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 0.2 GB to 69.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
35B A3B – a Qwen3.5 MoE decision model for browser actions
35B A3B is a 35‑billion‑parameter Qwen3.5 MoE model with 3 active experts. It is trained for decision tasks such as selecting browser actions and workflow steps. The model is available in GGUF format for llama.cpp, Ollama and LM Studio.
Good at
- Decision making for browser actions
- Selecting workflow steps
- Evaluating natural‑language criteria
Limits
- Requires 75 GB+ GPU memory for BF16 inference
- No chat or vision capabilities
- License is Apache‑2.0
Best for
- Automated browser testing
- Workflow orchestration
- Decision‑based AI assistants
Who it’s for. Developers building automated browsing agents or workflow engines that need a lightweight decision model. The model is not intended for general chat or vision tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_M | 21.2 GB | 22.3 GB | Too big | Get file → | |
| Q8_0 | 36.9 GB | 38.1 GB | Too big | Get file → | |
| BF16 | 69.4 GB (2 parts) | 70.5 GB | Too big | Get file → |
For 8 k context, Q4_K_M uses ~22 GB VRAM and 21 GB file size, suitable for mid‑range GPUs. Q8_0 needs ~38 GB VRAM and 37 GB file size, offering higher fidelity. BF16 requires ~70 GB VRAM and 70 GB file size, split into two shards.
What GPU do you need for 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: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 22.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 22.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).
Which 35B A3B quant should you choose?
Q4_K_M is the usual starting point for 35B A3B: it balances file size and quality well. Here it is a 21.2 GB file.
The Q8_0 file is 36.9 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 0.2 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 35B A3B
How much VRAM does 35B A3B need?
About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 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 35B A3B on an 8 GB GPU?
Yes, with the smaller files: the 0.2 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of 35B A3B GGUF?
It depends on the quant: file is 0.2 GB, Q4_K_M is 21.2 GB, Q8_0 is 36.9 GB, BF16 is 69.4 GB.
What context length does 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 2.7 GB at 32K.
Where can I download 35B A3B GGUF?
The files are on Hugging Face in the apus-ailab/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 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 35B A3B on 8 GB VRAM?
No. The smallest quant requires ~22 GB VRAM at 8 k context, so 8 GB is insufficient.
Does the model support vision or chat?
No. It is a decision model only and does not handle vision or chat.
What license applies to the model?
The model is released under the Apache‑2.0 license.