Capek0.5 35B A3B needs about 29.7 GB of memory at Q6_K (a 28.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 5 quants, from 19.8 GB (MXFP4_MOE) to 69.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Capek0.5 35B A3B – a vision‑language MoE model for embodied reasoning
Capek0.5 35B A3B is a 35B parameter vision‑language model built on Qwen3.6‑35B‑A3B. It uses a mixture of experts with 3B active parameters per token and supports spatial reasoning, temporal understanding, action guidance, and state verification.
Good at
- Spatial reasoning
- Temporal understanding
- Action guidance
Limits
- Requires large VRAM – 21 GB at 8 k context for MXFP4_MOE
- Limited to 8 k context for memory estimates
- Apache‑2.0 license restricts commercial redistribution
Best for
- Robotics task planning
- Embodied AI simulations
- Multimodal instruction following
Who it’s for. Developers building embodied AI systems that need spatial and temporal reasoning. Researchers working on vision‑language models for robotics and simulation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4_MOE | 19.8 GB | 21.0 GB | Too big | Get file → | |
| Q5_K_M | 24.7 GB | 25.9 GB | Too big | Get file → | |
| Q6_K | 28.5 GB | 29.7 GB | Too big | Get file → | |
| Q8_0 | 36.9 GB | 38.1 GB | Too big | Get file → | |
| BF16 | 69.4 GB | 70.5 GB | Too big | Get file → |
For 8 GB VRAM use Q5_K_M (25.9 GB estimate) or Q6_K (29.7 GB). For 16 GB VRAM use MXFP4_MOE (21 GB). For 32 GB VRAM use Q8_0 (38.1 GB). Estimates are approximate.
What GPU do you need for Capek0.5 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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is MXFP4_MOE (19.8 GB file, about 21.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 29.7 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 Capek0.5 35B A3B quant should you choose?
Q6_K (28.5 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is MXFP4_MOE at 19.8 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Capek0.5 35B A3B
How much VRAM does Capek0.5 35B A3B need?
About 29.7 GB at Q6_K with an 8K context window. That is the 28.5 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 Capek0.5 35B A3B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Capek0.5 35B A3B GGUF?
It depends on the quant: MXFP4_MOE is 19.8 GB, Q5_K_M is 24.7 GB, Q6_K is 28.5 GB, Q8_0 is 36.9 GB, BF16 is 69.4 GB.
What context length does Capek0.5 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 Capek0.5 35B A3B GGUF?
The files are on Hugging Face in the prithivMLmods/Capek0.5-35B-A3B-MXFP4-MoE-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 Capek0.5 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 Capek0.5 on 8 GB VRAM?
No, the smallest quant requires at least 21 GB of VRAM at 8 k context.
What is the maximum context length?
The model was trained with 262,144 tokens, but memory estimates are given for 8 k context.
Does the model support vision?
Yes, it accepts image and video inputs via the multimodal processor.