70B_unstruct needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 23 quants, from 0.0 GB to 49.9 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
70B_unstruct – a 70B llama model with reduced instruction overtraining
70B_unstruct is a 70.6B parameter llama model that merges Llama‑3.3‑Instruct with Llama‑3.1‑70B to reduce instruction overtraining and refusal pathways. It supports tool usage and has a 131072 token context window.
Good at
- Tool integration
- Reduced instruction overtraining
- Large context handling
Limits
- No vision support
- License not specified
- Large memory requirement
Best for
- Tool‑centric applications
- Long‑form content generation
- Custom instruction tuning
Who it’s for. Developers needing a large llama model with balanced instruction following and tool support. Suitable for research and production environments that can accommodate high memory usage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 3.2 GB | Fits | Get file → | |
| IQ1_S | 15.3 GB | 18.5 GB | Too big | Get file → | |
| IQ1_M | 16.8 GB | 19.9 GB | Too big | Get file → | |
| IQ2_XXS | 19.1 GB | 22.3 GB | Too big | Get file → | |
| IQ2_XS | 21.1 GB | 24.3 GB | Too big | Get file → | |
| IQ2_S | 22.2 GB | 25.4 GB | Too big | Get file → | |
| IQ2_M | 24.1 GB | 27.3 GB | Too big | Get file → | |
| Q2_K_S | 24.5 GB | 27.7 GB | Too big | Get file → | |
| Q2_K | 26.4 GB | 29.6 GB | Too big | Get file → | |
| IQ3_XXS | 27.5 GB | 30.7 GB | Too big | Get file → | |
| IQ3_XS | 29.3 GB | 32.5 GB | Too big | Get file → | |
| IQ3_S | 30.9 GB | 34.1 GB | Too big | Get file → | |
| Q3_K_S | 30.9 GB | 34.1 GB | Too big | Get file → | |
| IQ3_M | 31.9 GB | 35.1 GB | Too big | Get file → | |
| Q3_K_M | 34.3 GB | 37.5 GB | Too big | Get file → | |
| Q3_K_L | 37.1 GB | 40.3 GB | Too big | Get file → | |
| IQ4_XS | 37.9 GB | 41.1 GB | Too big | Get file → | |
| Q4_0 | 40.1 GB | 43.3 GB | Too big | Get file → | |
| Q4_K_S | 40.3 GB | 43.5 GB | Too big | Get file → | |
| Q4_K_M | 42.5 GB | 45.7 GB | Too big | Get file → | |
| Q4_1 | 44.3 GB | 47.5 GB | Too big | Get file → | |
| Q5_K_S | 48.7 GB | 51.8 GB | Too big | Get file → | |
| Q5_K_M | 49.9 GB | 53.1 GB | Too big | Get file → |
For 8‑GB VRAM use IQ1_S (15.34 GB, 18.5 GB memory at 8k). For 12‑GB VRAM use IQ1_M (16.75 GB, 19.9 GB). For 24‑GB VRAM use Q4_K_M (42.52 GB, 45.7 GB). Memory estimates are approximate.
What GPU do you need for 70B_unstruct?
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: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 24 GB VRAM: the best quant that fits is IQ2_XXS (19.1 GB file, about 22.3 GB in use).
- 32 GB VRAM: the best quant that fits is IQ3_XXS (27.5 GB file, about 30.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_1 (44.3 GB file, about 47.5 GB in use).
Which 70B_unstruct quant should you choose?
Q4_K_M is the usual starting point for 70B_unstruct: it balances file size and quality well. Here it is a 42.5 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about 70B_unstruct
How much VRAM does 70B_unstruct need?
About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 70B_unstruct on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of 70B_unstruct GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 15.3 GB, IQ1_M is 16.8 GB, IQ2_XXS is 19.1 GB, IQ2_XS is 21.1 GB, IQ2_S is 22.2 GB and 17 more.
What context length does 70B_unstruct support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download 70B_unstruct GGUF?
The files are on Hugging Face in the mradermacher/70B_unstruct-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 70B_unstruct on 8 GB VRAM?
Use the IQ1_S quant; it requires about 18.5 GB of VRAM at 8k context, so 8 GB is insufficient.
Does 70B_unstruct support vision?
No, the model has no vision capabilities.
What is the context length of 70B_unstruct?
The model supports 131072 tokens of context.