Apex 35B V1.0 needs about 26.5 GB of memory at Q5_K_M (a 25.3 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 6 quants, from 18.6 GB (Q3_K_L) to 71.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Apex 35B V1.0 – a 35B sparse Mixture‑of‑Experts model with 262K context
Apex 35B V1.0 is a 35.5B parameter sparse Mixture‑of‑Experts model built on qwen35moe. It offers a 262,144 token context window and supports reasoning, tool use, and vision. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.
Good at
- Long‑form reasoning
- Agentic coding and tool use
- Vision tasks
Limits
- No vision support in some quantizations
- Large VRAM required for full precision
- Requires 262K context window
Best for
- Research in scientific computing
- Robotics simulation workflows
- Complex multi‑turn tool interactions
Who it’s for. Researchers and developers needing a large‑context, sparse Mixture‑of‑Experts model for coding, scientific analysis, and agentic tasks. The model is open‑weight and can be fine‑tuned or used as a base for custom applications.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 18.6 GB | 19.7 GB | Too big | Get file → | |
| MXFP4_MOE | 20.3 GB | 21.4 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 → | |
| BF16 | 71.1 GB | 72.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q3_K_L (file size 18.55 GB, estimated 19.7 GB at 8 k context). For 12 GB VRAM, MXFP4_MOE (20.26 GB, 21.4 GB). For 16 GB VRAM, Q5_K_M (25.35 GB, 26.5 GB). Higher‑precision quants require more memory.
What GPU do you need for Apex 35B V1.0?
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 (20.3 GB file, about 21.4 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 Apex 35B V1.0 quant should you choose?
Q5_K_M (25.3 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is Q3_K_L at 18.6 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Apex 35B V1.0
How much VRAM does Apex 35B V1.0 need?
About 26.5 GB at Q5_K_M with an 8K context window. That is the 25.3 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 Apex 35B V1.0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 19.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Apex 35B V1.0 GGUF?
It depends on the quant: Q3_K_L is 18.6 GB, MXFP4_MOE is 20.3 GB, Q5_K_M is 25.3 GB, Q6_K is 29.2 GB, Q8_0 is 37.8 GB, BF16 is 71.1 GB.
What context length does Apex 35B V1.0 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 Apex 35B V1.0 GGUF?
The files are on Hugging Face in the prithivMLmods/Apex-35B-V1.0-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 Apex 35B V1.0 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 Apex 35B V1.0 on 8 GB VRAM?
Use the Q3_K_L quant, which has a file size of 18.55 GB and an estimated memory usage of 19.7 GB at 8 k context. It is the lowest‑memory option available.
Does the model support vision tasks?
Yes, the model has detected vision abilities, but some quantizations may not include the vision weights. Verify the quant file before use.
What license applies to Apex 35B V1.0?
The model is released under the Apache‑2.0 license, allowing free use and modification.