Nous Capybara limarpv3 34B i1 needs about 23.7 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 22 quants, from 8.1 GB (IQ1_S) to 28.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
Nous Capybara limarpv3 34B i1 – a 34‑billion‑parameter llama model in GGUF format
This model is a 34‑billion‑parameter llama architecture, trained on 200,000 context tokens. It is available in multiple quantizations from IQ1_S up to Q6_K. The model is provided by mradermacher and is based on the Nous Capybara limarpv3 family.
Good at
- Large context handling
- High‑parameter inference
- Versatile quant options
Limits
- No vision support
- License not specified
- Requires large VRAM for full precision
Best for
- Research prototypes
- Custom fine‑tuning
- High‑capacity text generation
Who it’s for. Developers and researchers needing a large llama model for text tasks. The model can be run locally with llama.cpp using the provided GGUF files.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 8.1 GB | 10.6 GB | Too big | Get file → | |
| IQ1_M | 8.8 GB | 11.3 GB | Too big | Get file → | |
| IQ2_XXS | 9.9 GB | 12.4 GB | Too big | Get file → | |
| IQ2_XS | 10.9 GB | 13.4 GB | Too big | Get file → | |
| IQ2_S | 11.5 GB | 14.0 GB | Too big | Get file → | |
| IQ2_M | 12.4 GB | 14.9 GB | Too big | Get file → | |
| Q2_K | 13.4 GB | 15.9 GB | Too big | Get file → | |
| IQ3_XXS | 14.2 GB | 16.7 GB | Too big | Get file → | |
| Q3_K_XS | 14.7 GB | 17.2 GB | Too big | Get file → | |
| IQ3_XS | 14.8 GB | 17.3 GB | Too big | Get file → | |
| Q3_K_S | 15.5 GB | 18.0 GB | Too big | Get file → | |
| IQ3_S | 15.6 GB | 18.1 GB | Too big | Get file → | |
| IQ3_M | 16.1 GB | 18.6 GB | Too big | Get file → | |
| Q3_K_M | 17.2 GB | 19.7 GB | Too big | Get file → | |
| Q3_K_L | 18.7 GB | 21.2 GB | Too big | Get file → | |
| IQ4_XS | 19.0 GB | 21.5 GB | Too big | Get file → | |
| Q4_0 | 20.1 GB | 22.6 GB | Too big | Get file → | |
| Q4_K_S | 20.1 GB | 22.7 GB | Too big | Get file → | |
| Q4_K_M | 21.2 GB | 23.7 GB | Too big | Get file → | |
| Q5_K_S | 24.2 GB | 26.8 GB | Too big | Get file → | |
| Q5_K_M | 24.9 GB | 27.4 GB | Too big | Get file → | |
| Q6_K | 28.8 GB | 31.3 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (8.1 GB file, ~10.6 GB VRAM). For 12 GB VRAM, IQ2_XS (10.91 GB file, ~13.4 GB VRAM). For 16 GB VRAM, Q3_K_S (15.5 GB file, ~18 GB VRAM). Estimates are approximate.
What GPU do you need for Nous Capybara limarpv3 34B i1?
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 (8.8 GB file, about 11.3 GB in use).
- 16 GB VRAM: the best quant that fits is Q2_K (13.4 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 23.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.8 GB file, about 31.3 GB in use).
Which Nous Capybara limarpv3 34B i1 quant should you choose?
Q4_K_M is the usual starting point for Nous Capybara limarpv3 34B i1: it balances file size and quality well. Here it is a 21.2 GB file.
If memory is tight, the smallest file is IQ1_S at 8.1 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 Nous Capybara limarpv3 34B i1
How much VRAM does Nous Capybara limarpv3 34B i1 need?
About 23.7 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 Nous Capybara limarpv3 34B i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Nous Capybara limarpv3 34B i1 GGUF?
It depends on the quant: IQ1_S is 8.1 GB, IQ1_M is 8.8 GB, IQ2_XXS is 9.9 GB, IQ2_XS is 10.9 GB, IQ2_S is 11.5 GB, IQ2_M is 12.4 GB and 16 more.
What context length does Nous Capybara limarpv3 34B i1 support?
The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.
Where can I download Nous Capybara limarpv3 34B i1 GGUF?
The files are on Hugging Face in the mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Use the IQ1_S quant, which requires about 10.6 GB VRAM at 8k context. It is the smallest available quant.
Does this model support image input?
No, the model has no vision capabilities.
Where can I find the quantization files?
They are hosted on the Hugging Face repo mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF.