Llama3-18B-lingyang-v1 needs about 14.0 GB of memory at Q4_K_M (a 10.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 6.9 GB (Q2_K) to 19.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.5 GB.
18‑B Llama3 model with multiple GGUF quantizations
Llama3-18B-lingyang-v1 is a 18.1‑billion‑parameter Llama model. It offers a range of static GGUF quantizations from Q2_K to Q8_0. The model was merged from pre‑trained components and is available on Hugging Face.
Good at
- Large context handling
- High‑parameter language modeling
- Versatile quantization options
Limits
- No vision support
- License type is other
- Requires substantial VRAM for higher quants
Best for
- Research on large‑language‑model behavior
- Fine‑tuning with limited GPU memory
- Benchmarking quantization trade‑offs
Who it’s for. Researchers and developers needing a large Llama model with flexible quantization. The model is suitable for those who can manage the memory requirements of the higher‑quality quants.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 6.9 GB | 10.0 GB | Too big | Get file → | |
| IQ3_XS | 7.6 GB | 10.7 GB | Too big | Get file → | |
| Q3_K_S | 8.0 GB | 11.1 GB | Too big | Get file → | |
| IQ3_S | 8.0 GB | 11.1 GB | Too big | Get file → | |
| IQ3_M | 8.3 GB | 11.4 GB | Too big | Get file → | |
| Q3_K_M | 8.8 GB | 12.0 GB | Too big | Get file → | |
| Q3_K_L | 9.6 GB | 12.7 GB | Too big | Get file → | |
| IQ4_XS | 9.9 GB | 13.0 GB | Too big | Get file → | |
| Q4_K_S | 10.4 GB | 13.5 GB | Too big | Get file → | |
| Q4_K_M | 10.9 GB | 14.0 GB | Too big | Get file → | |
| Q5_K_S | 12.5 GB | 15.6 GB | Too big | Get file → | |
| Q5_K_M | 12.8 GB | 15.9 GB | Too big | Get file → | |
| Q6_K | 14.8 GB | 17.9 GB | Too big | Get file → | |
| Q8_0 | 19.2 GB | 22.3 GB | Too big | Get file → |
For 8‑GB VRAM, use Q2_K (6.87 GB file, 10 GB VRAM at 8 k context) or IQ3_XS (7.62 GB file, 10.7 GB VRAM). If 12 GB VRAM is available, Q4_K_M (10.92 GB file, 14 GB VRAM) offers better quality. Higher quants such as Q5_K_M or Q6_K need 15–18 GB VRAM.
What GPU do you need for Llama3-18B-lingyang-v1?
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: the best quant that fits is Q3_K_M (8.8 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (12.8 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (19.2 GB file, about 22.3 GB in use).
Which Llama3-18B-lingyang-v1 quant should you choose?
Q4_K_M is the usual starting point for Llama3-18B-lingyang-v1: it balances file size and quality well. Here it is a 10.9 GB file.
The Q8_0 file is 19.2 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 Q2_K at 6.9 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 Llama3-18B-lingyang-v1
How much VRAM does Llama3-18B-lingyang-v1 need?
About 14.0 GB at Q4_K_M with an 8K context window. That is the 10.9 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 Llama3-18B-lingyang-v1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama3-18B-lingyang-v1 GGUF?
It depends on the quant: Q2_K is 6.9 GB, IQ3_XS is 7.6 GB, Q3_K_S is 8.0 GB, IQ3_S is 8.0 GB, IQ3_M is 8.3 GB, Q3_K_M is 8.8 GB and 8 more.
What context length does Llama3-18B-lingyang-v1 support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 2.6 GB at 8K and 10.5 GB at 32K.
Where can I download Llama3-18B-lingyang-v1 GGUF?
The files are on Hugging Face in the mradermacher/Llama3-18B-lingyang-v1-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 Llama3-18B-lingyang-v1 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 Llama3-18B-lingyang-v1 on 8 GB VRAM?
Use Q2_K or IQ3_XS; they require about 10–10.7 GB VRAM at 8 k context.
Does the model support vision tasks?
No, the model has no vision capabilities.
Where can I find the quantized files?
They are hosted on Hugging Face under mradermacher/Llama3-18B-lingyang-v1-GGUF.