Capybara 31B GGUFS needs about 51.4 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 13 quants, from 16.5 GB (Q5_K_S) to 61.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.
Capybara 31B GGUFS – a fine‑tuned Gemma 4 model for local orchestration
Capybara 31B GGUFS is a fine‑tuned version of google/gemma-4-31B-it. It is designed for front‑desk orchestration in multi‑agent setups, summarizing context and delegating tasks. The model focuses on reasoning, clear communication, and honesty.
Good at
- Reasoning and task decomposition
- Clear communication
- Orchestration of multi‑agent workflows
Limits
- No vision or audio support
- Large memory requirement for full precision
- Not production‑ready
Best for
- Local orchestrator in multi‑agent systems
- Summarizing complex context
- Routing tasks to specialized agents
Who it’s for. Developers building local AI assistants that need a reliable front‑desk agent. It is suitable for environments with sufficient GPU memory and where fine‑tuned orchestration is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_S | 16.5 GB | 49.2 GB | Too big | Get file → | |
| IQ4_XS | 16.9 GB | 49.6 GB | Too big | Get file → | |
| Q4_0 | 17.7 GB | 50.4 GB | Too big | Get file → | |
| IQ4_NL | 17.8 GB | 50.5 GB | Too big | Get file → | |
| Q4_K_S | 17.8 GB | 50.5 GB | Too big | Get file → | |
| Q4_K_M | 18.7 GB | 51.4 GB | Too big | Get file → | |
| Q4_1 | 19.5 GB | 52.2 GB | Too big | Get file → | |
| Q5_0 | 21.3 GB | 54.0 GB | Too big | Get file → | |
| Q5_K_M | 21.8 GB | 54.6 GB | Too big | Get file → | |
| Q5_1 | 23.1 GB | 55.9 GB | Too big | Get file → | |
| Q6_K | 25.2 GB | 57.9 GB | Too big | Get file → | |
| Q8_0 | 32.6 GB | 65.3 GB | Too big | Get file → | |
| F16 | 61.4 GB | 94.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q5_K_S (16.51 GB file, 49.2 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (18.69 GB file, 51.4 GB memory) is a good balance. For 16 GB VRAM, Q5_K_M (21.85 GB file, 54.6 GB memory) offers higher quality.
What GPU do you need for Capybara 31B GGUFS?
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: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Capybara 31B GGUFS quant should you choose?
Q4_K_M is the usual starting point for Capybara 31B GGUFS: it balances file size and quality well. Here it is a 18.7 GB file.
The Q8_0 file is 32.6 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 Q5_K_S at 16.5 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Capybara 31B GGUFS
How much VRAM does Capybara 31B GGUFS need?
About 51.4 GB at Q4_K_M with an 8K context window. That is the 18.7 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 Capybara 31B GGUFS on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 49.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Capybara 31B GGUFS GGUF?
It depends on the quant: Q5_K_S is 16.5 GB, IQ4_XS is 16.9 GB, Q4_0 is 17.7 GB, IQ4_NL is 17.8 GB, Q4_K_S is 17.8 GB, Q4_K_M is 18.7 GB and 7 more.
What context length does Capybara 31B GGUFS support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.
Where can I download Capybara 31B GGUFS GGUF?
The files are on Hugging Face in the TendieLabs/Capybara-31B-GGUFS repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Capybara 31B GGUFS use?
Hugging Face lists the license as gemma. 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 Capybara 31B on 8 GB VRAM?
Use the Q5_K_S quantized file; it requires about 49.2 GB memory at 8 k context, which exceeds 8 GB VRAM, so it is not feasible.
Does this model support image input?
No, Capybara 31B does not support vision or audio input.
Is this model production ready?
No, it is an experimental release and not intended for production use.