Meta-Llama-3-120B-Instruct needs about 78.4 GB of memory at Q4_K_M (a 73.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 13 quants, from 26.0 GB (IQ1_S) to 129.5 GB (Q8_0).
Meta-Llama-3-120B-Instruct, a 120‑billion‑parameter Llama 3 model for creative writing
Meta-Llama-3-120B-Instruct is a 120‑billion‑parameter Llama 3 model created via self‑merge. It uses the Llama 3 chat template with an 8K context window. The model excels at creative writing but may produce typos and excessive uppercase.
Good at
- Creative writing
- Llama 3 chat template
- Large context handling
Limits
- Large VRAM requirement
- No vision support
- License is other
Best for
- Writing fiction or poetry
- Generating long creative prompts
- Exploring Llama 3 chat style
Who it’s for. Developers and writers who need a large Llama 3 model for creative tasks. The model is suitable for local inference with sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 26.0 GB | 31.2 GB | Too big | Get file → | |
| IQ1_M | 28.5 GB | 33.7 GB | Too big | Get file → | |
| IQ2_M | 41.3 GB | 46.5 GB | Too big | Get file → | |
| Q2_K | 45.1 GB | 50.3 GB | Too big | Get file → | |
| Q3_K_S | 52.8 GB (2 parts) | 58.0 GB | Too big | Get file → | |
| Q3_K_M | 58.8 GB (2 parts) | 64.0 GB | Too big | Get file → | |
| Q3_K_L | 64.0 GB (2 parts) | 69.2 GB | Too big | Get file → | |
| Q4_K_S | 69.4 GB (3 parts) | 74.6 GB | Too big | Get file → | |
| Q4_K_M | 73.2 GB (3 parts) | 78.4 GB | Too big | Get file → | |
| Q5_K_S | 84.0 GB (3 parts) | 89.2 GB | Too big | Get file → | |
| Q5_K_M | 86.2 GB (3 parts) | 91.4 GB | Too big | Get file → | |
| Q6_K | 100.0 GB (4 parts) | 105.2 GB | Too big | Get file → | |
| Q8_0 | 129.5 GB (5 parts) | 134.7 GB | Too big | Get file → |
For 8‑GB VRAM use Q4_K_S (69.35 GB file, ~74.6 GB memory at 8K). For 16‑GB VRAM use Q4_K_M (73.24 GB file, ~78.4 GB memory). For 24‑GB VRAM use Q5_K_S (83.96 GB file, ~89.2 GB memory). Estimates are approximate.
What GPU do you need for Meta-Llama-3-120B-Instruct?
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 IQ1_S (26.0 GB file, about 31.2 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_M (41.3 GB file, about 46.5 GB in use).
Which Meta-Llama-3-120B-Instruct quant should you choose?
Q4_K_M is the usual starting point for Meta-Llama-3-120B-Instruct: it balances file size and quality well. Here it is a 73.2 GB file.
The Q8_0 file is 129.5 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ1_S at 26.0 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 Meta-Llama-3-120B-Instruct
How much VRAM does Meta-Llama-3-120B-Instruct need?
About 78.4 GB at Q4_K_M with an 8K context window. That is the 73.2 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 Meta-Llama-3-120B-Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 31.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Meta-Llama-3-120B-Instruct GGUF?
It depends on the quant: IQ1_S is 26.0 GB, IQ1_M is 28.5 GB, IQ2_M is 41.3 GB, Q2_K is 45.1 GB, Q3_K_S is 52.8 GB, Q3_K_M is 58.8 GB and 7 more.
What context length does Meta-Llama-3-120B-Instruct support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 4.7 GB at 8K and 4.7 GB at 8K.
Where can I download Meta-Llama-3-120B-Instruct GGUF?
The files are on Hugging Face in the lmstudio-community/Meta-Llama-3-120B-Instruct-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 Meta-Llama-3-120B-Instruct 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 Meta‑Llama‑3‑120B‑Instruct on 8 GB VRAM?
Only with a very low‑precision quant like Q4_K_S, which still requires about 74.6 GB of VRAM at 8K context.
Does this model support image input?
No, the model has no vision capability.
What is the context window size?
The default context window is 8,192 tokens, extendable with rope theta.