Nous Puffin 70B needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 25.5 GB (Q2_K) to 48.8 GB (Q5_K_M).
Nous Puffin 70B – a 70B‑parameter Llama‑2 fine‑tuned model
Nous Puffin 70B is a 70B‑parameter Llama‑2 model fine‑tuned on 3,000 high‑quality GPT‑4 examples and curated domain data. It supports a 4,096‑token context window and is released under the MIT license.
Good at
- Long‑form conversation
- Creative brainstorming
- Domain‑specific knowledge up to 2023
Limits
- No vision support
- Requires large VRAM for full precision
- No mixture‑of‑experts
Best for
- Chatbots needing deep context
- Creative writing assistants
- Research assistants for science domains
Who it’s for. Developers and researchers who need a large, context‑rich language model for local deployment. The model is suitable for applications that can accommodate the memory demands of a 70B‑parameter Llama‑2 model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 25.5 GB | 27.3 GB | Too big | Get file → | |
| IQ3_XS | 28.3 GB | 30.2 GB | Too big | Get file → | |
| IQ3_S | 29.9 GB | 31.8 GB | Too big | Get file → | |
| Q3_K_S | 29.9 GB | 31.8 GB | Too big | Get file → | |
| IQ3_M | 30.9 GB | 32.8 GB | Too big | Get file → | |
| Q3_K_M | 33.3 GB | 35.1 GB | Too big | Get file → | |
| Q3_K_L | 36.1 GB | 38.0 GB | Too big | Get file → | |
| IQ4_XS | 37.2 GB | 39.0 GB | Too big | Get file → | |
| Q4_K_S | 39.2 GB | 41.1 GB | Too big | Get file → | |
| Q4_K_M | 41.4 GB | 43.3 GB | Too big | Get file → | |
| Q5_K_S | 47.5 GB | 49.3 GB | Too big | Get file → | |
| Q5_K_M | 48.8 GB | 50.6 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (25.46 GB). For 12 GB VRAM use IQ3_XS (28.31 GB). For 16 GB VRAM use Q3_K_S (29.92 GB). Estimates are approximate.
What GPU do you need for Nous Puffin 70B?
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 IQ3_XS (28.3 GB file, about 31.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).
Which Nous Puffin 70B quant should you choose?
Q4_K_M is the usual starting point for Nous Puffin 70B: it balances file size and quality well. Here it is a 41.4 GB file.
If memory is tight, the smallest file is Q2_K at 25.5 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 Puffin 70B
How much VRAM does Nous Puffin 70B need?
About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 Puffin 70B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 28.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Nous Puffin 70B GGUF?
It depends on the quant: Q2_K is 25.5 GB, IQ3_XS is 28.3 GB, IQ3_S is 29.9 GB, Q3_K_S is 29.9 GB, IQ3_M is 30.9 GB, Q3_K_M is 33.3 GB and 6 more.
What context length does Nous Puffin 70B support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.
Where can I download Nous Puffin 70B GGUF?
The files are on Hugging Face in the mradermacher/Nous-Puffin-70B-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 Nous Puffin 70B use?
Hugging Face lists the license as mit. 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 Nous Puffin 70B on 8 GB VRAM?
Use the Q2_K quant, which is 25.46 GB and requires about 28.6 GB of VRAM at 8k context.
Does this model support vision tasks?
No, the model has no vision capability.
What license does it use?
The model is released under the MIT license.