L3.1 Meta In 15B i1 needs about 11.8 GB of memory at Q4_K_M (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 22 quants, from 3.5 GB (IQ1_S) to 12.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
15B parameter Meta Llama 3.1 Instruct model in GGUF format
L3.1 Meta In 15B i1 is a 15B parameter language model based on Meta Llama 3.1. It was merged with NousResearch/Meta-Llama-3.1-8B-Instruct using passthrough merge. The model supports a context length of 131072 tokens.
Good at
- Large context handling
- Instruct style responses
- High token capacity
Limits
- No vision support
- License not specified
- Requires significant VRAM for higher quants
Best for
- Chatbot backends
- Long-form content generation
- Research prototyping
Who it’s for. Developers and researchers needing a large-context Llama 3.1 model in GGUF format. Suitable for environments where 8‑k context is sufficient and GPU memory allows the chosen quant.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.5 GB | 6.1 GB | Fits | Get file → | |
| IQ1_M | 3.8 GB | 6.4 GB | Fits | Get file → | |
| IQ2_XXS | 4.3 GB | 6.9 GB | Fits | Get file → | |
| IQ2_XS | 4.7 GB | 7.3 GB | Tight | Get file → | |
| IQ2_S | 4.9 GB | 7.6 GB | Tight | Get file → | |
| IQ2_M | 5.3 GB | 7.9 GB | Tight | Get file → | |
| Q2_K_S | 5.4 GB | 8.0 GB | Too big | Get file → | |
| Q2_K | 5.7 GB | 8.4 GB | Too big | Get file → | |
| IQ3_XXS | 6.0 GB | 8.6 GB | Too big | Get file → | |
| IQ3_XS | 6.4 GB | 9.0 GB | Too big | Get file → | |
| Q3_K_S | 6.7 GB | 9.3 GB | Too big | Get file → | |
| IQ3_S | 6.7 GB | 9.3 GB | Too big | Get file → | |
| IQ3_M | 6.9 GB | 9.6 GB | Too big | Get file → | |
| Q3_K_M | 7.4 GB | 10.0 GB | Too big | Get file → | |
| Q3_K_L | 8.0 GB | 10.6 GB | Too big | Get file → | |
| IQ4_XS | 8.2 GB | 10.8 GB | Too big | Get file → | |
| Q4_0 | 8.6 GB | 11.3 GB | Too big | Get file → | |
| Q4_K_S | 8.6 GB | 11.3 GB | Too big | Get file → | |
| Q4_K_M | 9.1 GB | 11.8 GB | Too big | Get file → | |
| Q5_K_S | 10.4 GB | 13.0 GB | Too big | Get file → | |
| Q5_K_M | 10.7 GB | 13.3 GB | Too big | Get file → | |
| Q6_K | 12.3 GB | 15.0 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (file size 3.5 GB, estimated 6.1 GB memory). For 12‑GB VRAM, IQ2_XS (4.67 GB, 7.3 GB memory) or Q2_K (5.75 GB, 8.4 GB memory). Higher quants such as Q4_K_M or Q5_K_M require 11.8 GB or 13.3 GB memory respectively.
What GPU do you need for L3.1 Meta In 15B i1?
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: the best quant that fits is Q2_K_S (5.4 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_M (9.1 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.3 GB file, about 15.0 GB in use).
Which L3.1 Meta In 15B i1 quant should you choose?
Q4_K_M is the usual starting point for L3.1 Meta In 15B i1: it balances file size and quality well. Here it is a 9.1 GB file.
If memory is tight, the smallest file is IQ1_S at 3.5 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 L3.1 Meta In 15B i1
How much VRAM does L3.1 Meta In 15B i1 need?
About 11.8 GB at Q4_K_M with an 8K context window. That is the 9.1 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 L3.1 Meta In 15B i1 on an 8 GB GPU?
Yes, with Q2_K_S: the 5.4 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of L3.1 Meta In 15B i1 GGUF?
It depends on the quant: IQ1_S is 3.5 GB, IQ1_M is 3.8 GB, IQ2_XXS is 4.3 GB, IQ2_XS is 4.7 GB, IQ2_S is 4.9 GB, IQ2_M is 5.3 GB and 16 more.
What context length does L3.1 Meta In 15B i1 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download L3.1 Meta In 15B i1 GGUF?
The files are on Hugging Face in the mradermacher/L3.1-Meta-In-15B-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 this model on 8 GB VRAM?
Yes, the IQ1_S quant uses about 6.1 GB memory at 8k context, fitting within 8 GB VRAM.
Does this model support vision tasks?
No, the model has no vision capabilities.
Where can I find the quantized files?
Quantized GGUF files are available at the Hugging Face repo mradermacher/L3.1-Meta-In-15B-i1-GGUF.