Tiel Coder 35B A3B Genesis Hermes needs about 22.3 GB of memory at its main file (a 21.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 20.2 GB to 38.5 GB (Q8_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Tiel Coder 35B A3B Genesis Hermes – a 34.7B parameter coding LLM with vision and tool support
Tiel Coder 35B A3B Genesis Hermes is a 34.7B parameter mixture‑of‑experts model based on qwen35moe. It supports coding, tool use, and vision tasks. The model is released under the MIT license and offers a large 262144 token context window.
Good at
- Advanced coding
- Tool integration
- Vision tasks
Limits
- Requires large VRAM for full context
- Mixture of experts limits single‑token throughput
- No dedicated vision model support beyond basic
Best for
- Complex code generation
- Automated tool usage
- Image‑based code analysis
Who it’s for. Developers and researchers needing a versatile coding assistant that can interact with tools and process visual input. The model is suitable for projects that can accommodate its memory requirements and benefit from a mixture‑of‑experts architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 20.2 GB | 21.4 GB | Too big | Get file → | |
| — | 21.1 GB | 22.3 GB | Too big | Get file → | |
| Q8_K_XL | 38.5 GB | 39.6 GB | Too big | Get file → |
For 8k context, the unknown quant file (~20.19 GB) needs ~21.4 GB VRAM. The larger unknown quant (~21.09 GB) needs ~22.3 GB VRAM. The Q8_K_XL quant (~38.45 GB) requires ~39.6 GB VRAM. Choose the smallest file that fits your VRAM budget.
What GPU do you need for Tiel Coder 35B A3B Genesis Hermes?
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 the main file (21.1 GB file, about 22.3 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (21.1 GB file, about 22.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_K_XL (38.5 GB file, about 39.6 GB in use).
Which Tiel Coder 35B A3B Genesis Hermes quant should you choose?
If memory is tight, the smallest file is the first one in the table at 20.2 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 Tiel Coder 35B A3B Genesis Hermes
How much VRAM does Tiel Coder 35B A3B Genesis Hermes need?
About 22.3 GB at its main file with an 8K context window. That is the 21.1 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 Tiel Coder 35B A3B Genesis Hermes on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Tiel Coder 35B A3B Genesis Hermes GGUF?
It depends on the quant: file is 20.2 GB, file is 21.1 GB, Q8_K_XL is 38.5 GB.
What context length does Tiel Coder 35B A3B Genesis Hermes 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 Tiel Coder 35B A3B Genesis Hermes GGUF?
The files are on Hugging Face in the LuffyTheFox/Tiel-Coder-35B-A3B-Genesis-Hermes-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 Tiel Coder 35B A3B Genesis Hermes use?
Hugging Face lists the license as mit. 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 this model on 8 GB VRAM?
No. The smallest quant requires at least 21.4 GB VRAM for 8k context.
Does it support vision tasks?
Yes, it has detected vision abilities but no dedicated vision model is provided.
What license does it use?
The model is released under the MIT license.