timdettmers_guanaco-65b needs about 61.3 GB of memory at Q4_K_M (a 39.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 10 quants, from 27.0 GB (Q2_K) to 46.2 GB (Q5_K_M).
Guanaco 65B – 65.3B‑parameter LLaMA finetuned chatbot
Guanaco 65B is a 65.3B‑parameter LLaMA model fine‑tuned with 4‑bit QLoRA on the OASST1 dataset. It is available in multiple quantizations and is intended for research and local experimentation. The model is released under an Apache 2 license and requires LLaMA weights.
Good at
- Chatbot dialogue
- Open‑source research
- Low‑cost local inference
Limits
- No vision support
- Requires LLaMA base weights
- Inference is slow in 4‑bit
Best for
- Research prototyping
- Local chatbot demos
- Educational experiments
Who it’s for. Researchers and developers who need a large‑scale LLaMA‑based chatbot that can be run locally. The model is suitable for experimentation with 4‑bit QLoRA finetuning and for building low‑cost chatbot prototypes.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 27.0 GB | 32.9 GB | Too big | Get file → | |
| Q3_K_S | 28.2 GB | 34.0 GB | Too big | Get file → | |
| Q3_K_M | 31.6 GB | 37.4 GB | Too big | Get file → | |
| Q3_K_L | 34.6 GB | 40.5 GB | Too big | Get file → | |
| Q4_0 | 36.8 GB | 42.7 GB | Too big | Get file → | |
| Q4_K_S | 36.9 GB | 42.8 GB | Too big | Get file → | |
| Q4_K_M | 39.3 GB | 45.2 GB | Too big | Get file → | |
| Q5_0 | 44.9 GB | 50.8 GB | Too big | Get file → | |
| Q5_K_S | 44.9 GB | 50.8 GB | Too big | Get file → | |
| Q5_K_M | 46.2 GB | 52.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 36.8 GB, estimated 58.8 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (39.35 GB, 61.3 GB memory) is a good balance. If more VRAM is available, Q5_K_M (46.24 GB, 68.2 GB memory) offers higher quality.
What GPU do you need for timdettmers_guanaco-65b?
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 timdettmers_guanaco-65b quant should you choose?
Q4_K_M is the usual starting point for timdettmers_guanaco-65b: it balances file size and quality well. Here it is a 39.3 GB file.
If memory is tight, the smallest file is Q2_K at 27.0 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 timdettmers_guanaco-65b
How much VRAM does timdettmers_guanaco-65b need?
About 61.3 GB at Q4_K_M with an 8K context window. That is the 39.3 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 timdettmers_guanaco-65b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 49.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of timdettmers_guanaco-65b GGUF?
It depends on the quant: Q2_K is 27.0 GB, Q3_K_S is 28.2 GB, Q3_K_M is 31.6 GB, Q3_K_L is 34.6 GB, Q4_0 is 36.8 GB, Q4_K_S is 36.9 GB and 4 more.
What context length does timdettmers_guanaco-65b support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 21.5 GB at 8K and 5.4 GB at 2K.
Where can I download timdettmers_guanaco-65b GGUF?
The files are on Hugging Face in the TheBloke/guanaco-65B-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 timdettmers_guanaco-65b use?
Hugging Face lists the license as other. 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 Guanaco 65B on 8 GB VRAM?
Use the Q4_0 quantization; it requires about 58.8 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does Guanaco 65B support image input?
No, the model has no vision capabilities.
What license applies to Guanaco 65B?
The adapter weights are under Apache 2; the base LLaMA weights are governed by the LLaMA license.