AgentWorld 35B A3B Heretic needs about 22.4 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 19.7 GB (Q4_0) to 36.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
AgentWorld 35B A3B Heretic – a 34.7B parameter language world model
AgentWorld 35B A3B Heretic is a 34.7B parameter language world model built on Qwen architecture. It simulates agent–environment interactions across seven domains and supports reasoning, tools, and vision. The model is released under the apache-2.0 license.
Good at
- Agentic environment simulation
- Long chain‑of‑thought reasoning
- Multi‑domain tool calling
Limits
- No vision support in this GGUF build
- Large VRAM requirement for higher quantizations
- Requires 8k context for memory estimates
Best for
- Simulating agentic tasks in MCP, Search, Terminal, SWE, Android, Web, OS
- Testing agentic reasoning pipelines
- Evaluating multi‑domain tool usage
Who it’s for. Developers and researchers building or testing agentic systems that need realistic environment simulation. The model is suitable for those who can run large‑parameter LLMs and require a native world model rather than a generic policy model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 19.7 GB | 20.9 GB | Too big | Get file → | |
| Q4_K_M | 21.2 GB | 22.4 GB | Too big | Get file → | |
| Q5_K_M | 24.7 GB | 25.9 GB | Too big | Get file → | |
| Q8_0 | 36.9 GB | 38.1 GB | Too big | Get file → |
For 8 GB VRAM use the Q4_0 quantization (file size 19.72 GB, estimated 20.9 GB memory at 8k context). For 16 GB VRAM the Q4_K_M quant (21.17 GB, 22.4 GB memory) is suitable. The Q5_K_M and Q8_0 quantizations require more than 32 GB VRAM and are not recommended for limited hardware.
What GPU do you need for AgentWorld 35B A3B Heretic?
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 Q4_K_M (21.2 GB file, about 22.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (24.7 GB file, about 25.9 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 AgentWorld 35B A3B Heretic quant should you choose?
Q4_K_M is the usual starting point for AgentWorld 35B A3B Heretic: 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 Q4_0 at 19.7 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about AgentWorld 35B A3B Heretic
How much VRAM does AgentWorld 35B A3B Heretic need?
About 22.4 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 AgentWorld 35B A3B Heretic on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of AgentWorld 35B A3B Heretic GGUF?
It depends on the quant: Q4_0 is 19.7 GB, Q4_K_M is 21.2 GB, Q5_K_M is 24.7 GB, Q8_0 is 36.9 GB.
What context length does AgentWorld 35B A3B Heretic 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 AgentWorld 35B A3B Heretic GGUF?
The files are on Hugging Face in the auttasak88/AgentWorld-35B-A3B-Heretic repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does AgentWorld 35B A3B Heretic 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 AgentWorld 35B A3B Heretic on 8 GB VRAM?
Yes, using the Q4_0 quantization which estimates 20.9 GB memory at 8k context, but actual VRAM usage may be higher due to overhead.
Does this model support vision tasks?
The provided GGUF build does not include vision support; it focuses on language and tool interactions.
What license applies to this model?
The model is released under the apache-2.0 license, allowing free use and modification.