LL

Llama3.1 16B Upscaled i1

LlamaGGUF by mradermacherUpdated 2025-01-27
Download on Hugging Face
Parameters15B
Context128K
Layers64
Architecturellama
Smallest quant5.3 GB
Quick answer

Llama3.1 16B Upscaled 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 7 quants, from 5.3 GB (IQ2_M) to 9.1 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Llama3.1 16B Upscaled i1 is a 15B-parameter Llama model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 7 quant files, from 5.3 GB (IQ2_M) to 9.1 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M5.3 GB 7.9 GB
Tight Get file →
Q2_K5.7 GB 8.4 GB
Too big Get file →
IQ3_XXS6.0 GB 8.6 GB
Too big Get file →
IQ3_M6.9 GB 9.6 GB
Too big Get file →
IQ4_NL8.6 GB 11.3 GB
Too big Get file →
Q4_K_S8.6 GB 11.3 GB
Too big Get file →
Q4_K_M9.1 GB 11.8 GB
Too big Get file →

What GPU do you need for Llama3.1 16B Upscaled 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 IQ2_M (5.3 GB file, about 7.9 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).

Which Llama3.1 16B Upscaled i1 quant should you choose?

Q4_K_M is the usual starting point for Llama3.1 16B Upscaled i1: it balances file size and quality well. Here it is a 9.1 GB file.

If memory is tight, the smallest file is IQ2_M at 5.3 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

Architecturellama
Parameters15B
Layers64
Trained context131,072 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyLlama
Downloads (HF)22
Last updated2025-01-27

Frequently asked questions about Llama3.1 16B Upscaled i1

How much VRAM does Llama3.1 16B Upscaled 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 Llama3.1 16B Upscaled i1 on an 8 GB GPU?

Yes, with IQ2_M: the 5.3 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama3.1 16B Upscaled i1 GGUF?

It depends on the quant: IQ2_M is 5.3 GB, Q2_K is 5.7 GB, IQ3_XXS is 6.0 GB, IQ3_M is 6.9 GB, IQ4_NL is 8.6 GB, Q4_K_S is 8.6 GB and 1 more.

What context length does Llama3.1 16B Upscaled 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 Llama3.1 16B Upscaled i1 GGUF?

The files are on Hugging Face in the mradermacher/Llama3.1-16B-Upscaled-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Llama3.1-16B-Upscaled

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other medium models

All medium models →