Apex-35B-V1.0 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 29 quants, from 9.0 GB (IQ1_S) 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 – 35B sparse mixture‑of‑experts model with 262,144‑token context
Apex-35B-V1.0 is a 35.5B parameter sparse mixture‑of‑experts model built on Qwen3.6-35B-A3B. It supports a 262,144‑token context window and dynamic reasoning. The model is licensed under apache-2.0 and is available in multiple GGUF quantizations.
Good at
- Reasoning
- Tool use
- Long‑context code and research tasks
Limits
- Requires large VRAM for high‑quality quants
- No vision support
- License is apache-2.0
Best for
- Research workflows
- Complex code generation
- Long‑form multi‑turn dialogue
Who it’s for. Researchers and developers needing a large, sparse model with extensive context. The model is suitable for scientific, engineering, and robotics simulation tasks that benefit from dynamic reasoning and tool integration.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 9.0 GB | 10.2 GB | Too big | Get file → | |
| IQ1_M | 9.9 GB | 11.1 GB | Too big | Get file → | |
| IQ2_XXS | 11.3 GB | 12.5 GB | Too big | Get file → | |
| IQ2_XS | 11.7 GB | 12.9 GB | Too big | Get file → | |
| IQ2_S | 12.5 GB | 13.6 GB | Too big | Get file → | |
| IQ2_M | 13.7 GB | 14.9 GB | Too big | Get file → | |
| Q2_K | 14.3 GB | 15.5 GB | Too big | Get file → | |
| IQ3_XXS | 16.1 GB | 17.2 GB | Too big | Get file → | |
| IQ3_XS | 16.8 GB | 18.0 GB | Too big | Get file → | |
| Q3_K_S | 16.8 GB | 18.0 GB | Too big | Get file → | |
| Q3_K_M | 17.8 GB | 19.0 GB | Too big | Get file → | |
| IQ3_S | 18.1 GB | 19.3 GB | Too big | Get file → | |
| Q3_K_L | 18.7 GB | 19.9 GB | Too big | Get file → | |
| IQ3_M | 19.4 GB | 20.6 GB | Too big | Get file → | |
| MXFP4_MOE | 20.3 GB | 21.5 GB | Too big | Get file → | |
| IQ4_XS | 20.4 GB | 21.6 GB | Too big | Get file → | |
| Q4_0 | 20.4 GB | 21.6 GB | Too big | Get file → | |
| Q4_K_S | 21.4 GB | 22.6 GB | Too big | Get file → | |
| Q4_K_M | 21.7 GB | 22.9 GB | Too big | Get file → | |
| Q4_1 | 22.4 GB | 23.6 GB | Too big | Get file → | |
| IQ4_NL | 22.8 GB | 24.0 GB | Too big | Get file → | |
| Q4_K_L | 24.6 GB | 25.8 GB | Too big | Get file → | |
| Q5_K_M | 25.3 GB | 26.5 GB | Too big | Get file → | |
| Q5_K_S | 25.6 GB | 26.8 GB | Too big | Get file → | |
| Q6_K | 29.2 GB | 30.4 GB | Too big | Get file → | |
| Q6_K_S | 29.9 GB | 31.0 GB | Too big | Get file → | |
| Q6_K_L | 32.8 GB | 34.0 GB | Too big | Get file → | |
| Q8_0 | 37.8 GB | 39.0 GB | Too big | Get file → | |
| BF16 | 71.1 GB (2 parts) | 72.3 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 8.97 GB, estimated memory 10.2 GB at 8 k context). For 16 GB VRAM, use Q4_K_M (file size 21.71 GB, estimated memory 22.9 GB). For 32 GB VRAM, use Q6_K (file size 29.21 GB, estimated memory 30.4 GB).
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: the best quant that fits is IQ1_M (9.9 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q2_K (14.3 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is IQ4_NL (22.8 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K_S (29.9 GB file, about 31.0 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?
Q4_K_M is the usual starting point for Apex-35B-V1.0: 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 IQ1_S at 9.0 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 Apex-35B-V1.0
How much VRAM does Apex-35B-V1.0 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 Apex-35B-V1.0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.2 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: IQ1_S is 9.0 GB, IQ1_M is 9.9 GB, IQ2_XXS is 11.3 GB, IQ2_XS is 11.7 GB, IQ2_S is 12.5 GB, IQ2_M is 13.7 GB and 23 more.
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 Apexintelligence-AI/Apex-35B-V1.0-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 IQ1_S quantization; it requires approximately 10.2 GB of VRAM at 8 k context, which is close to 8 GB but may need swapping.
Does the model support vision tasks?
No, Apex-35B-V1.0 does not include vision capabilities.
What is the context length of this model?
The model supports a context window of 262,144 tokens shared by input and output.