Agens-Volundr-32B-Preview needs about 29.5 GB of memory at Q4_K_M (a 26.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 26.6 GB (Q4_K_M) to 64.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 9.7 GB.
Agens Volundr 32B Preview – a 32B reasoning, coding, and agent model
Agens Volundr 32B Preview is a 32.2‑billion‑parameter model built on the volundr architecture. It supports coding, tool use, and long‑context reasoning with a 262144‑token context window. The model is released under the apache‑2.0 license.
Good at
- Coding and tool integration
- Long‑context reasoning
- Agent‑style interactions
Limits
- No vision support
- Requires volundr branch of llama.cpp
- Large VRAM needed for full context
Best for
- Developing coding assistants
- Building agentic workflows
- Testing long‑context LLM capabilities
Who it’s for. Engineers and researchers who need a large, open‑weights model for reasoning and coding tasks. The preview version is suitable for experimentation and early integration.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 26.6 GB | 29.5 GB | Too big | Get file → | |
| Q8_0 | 36.3 GB | 39.2 GB | Too big | Get file → | |
| BF16 | 64.5 GB | 67.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (26.6 GB file, ~29.5 GB memory at 8 k context). For 16 GB VRAM, Q8_0 (36.33 GB file, ~39.2 GB memory). BF16 requires >64 GB VRAM. Estimates are approximate.
What GPU do you need for Agens-Volundr-32B-Preview?
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: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q4_K_M (26.6 GB file, about 29.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (36.3 GB file, about 39.2 GB in use).
Which Agens-Volundr-32B-Preview quant should you choose?
Q4_K_M is the usual starting point for Agens-Volundr-32B-Preview: it balances file size and quality well. Here it is a 26.6 GB file.
The Q8_0 file is 36.3 GB, about 1.4 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Agens-Volundr-32B-Preview
How much VRAM does Agens-Volundr-32B-Preview need?
About 29.5 GB at Q4_K_M with an 8K context window. That is the 26.6 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 Agens-Volundr-32B-Preview on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 29.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Agens-Volundr-32B-Preview GGUF?
It depends on the quant: Q4_K_M is 26.6 GB, Q8_0 is 36.3 GB, BF16 is 64.5 GB.
What context length does Agens-Volundr-32B-Preview support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.4 GB at 8K and 9.7 GB at 32K.
Where can I download Agens-Volundr-32B-Preview GGUF?
The files are on Hugging Face in the Blockway/Agens-Volundr-32B-Preview-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 Agens-Volundr-32B-Preview 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 Agens Volundr 32B Preview on 8 GB VRAM?
Use the Q4_K_M quantised file; it requires about 29.5 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does this model support image inputs?
No, the preview supports text only.
What license applies to this model?
The model is released under the apache‑2.0 license.