Llama 2 70B Chat 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 10 quants, from 29.3 GB (Q2_K) to 48.8 GB (Q5_K_M).
Llama 2 70B Chat in GGUF format
Llama 2 70B Chat is a large language model with 70 billion parameters. It is available in GGUF format for efficient local inference. The model supports a 4096‑token context window and is licensed under the llama2 license.
Good at
- High‑quality conversational responses
- Large context handling
- Versatile language support
Limits
- Requires high VRAM for full precision
- No vision capabilities
- License restricts commercial use
Best for
- Chatbot development
- Research prototyping
- Content generation
Who it’s for. Developers and researchers needing a powerful conversational model for local deployment. The model is suitable for projects that can accommodate its memory requirements and comply with the llama2 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 29.3 GB | 31.1 GB | Too big | Get file → | |
| Q3_K_S | 29.9 GB | 31.8 GB | Too big | Get file → | |
| Q5_K_S | 30.6 GB | 32.4 GB | Too big | Get file → | |
| Q3_K_M | 33.2 GB | 35.0 GB | Too big | Get file → | |
| Q3_K_L | 36.1 GB | 38.0 GB | Too big | Get file → | |
| Q4_0 | 38.9 GB | 40.7 GB | Too big | Get file → | |
| Q4_K_S | 39.1 GB | 40.9 GB | Too big | Get file → | |
| Q4_K_M | 41.4 GB | 43.3 GB | Too big | Get file → | |
| Q5_0 | 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 Q4_K_S (39 GB file, ~42 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (41 GB file, ~44 GB memory). For 16 GB VRAM, Q5_K_M (48 GB file, ~52 GB memory). Estimates are approximate.
What GPU do you need for Llama 2 70B Chat?
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: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).
Which Llama 2 70B Chat quant should you choose?
Q4_K_M is the usual starting point for Llama 2 70B Chat: 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 29.3 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 Llama 2 70B Chat
How much VRAM does Llama 2 70B Chat 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 Llama 2 70B Chat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 32.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama 2 70B Chat GGUF?
It depends on the quant: Q2_K is 29.3 GB, Q3_K_S is 29.9 GB, Q5_K_S is 30.6 GB, Q3_K_M is 33.2 GB, Q3_K_L is 36.1 GB, Q4_0 is 38.9 GB and 4 more.
What context length does Llama 2 70B Chat 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 Llama 2 70B Chat GGUF?
The files are on Hugging Face in the TheBloke/Llama-2-70B-Chat-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 Llama 2 70B Chat use?
Hugging Face lists the license as llama2. 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 Llama 2 70B Chat on 8 GB VRAM?
Use the Q4_K_S quantised model; it requires about 42 GB of VRAM at 8 k context, which exceeds 8 GB, so it is not feasible.
What is the context length of this model?
The model supports a 4096‑token context window.
Is this model suitable for vision tasks?
No, the model has no vision capabilities.