LL

Llama 3.1 11b pretrained i1

LlamaGGUF by mradermacherUpdated 2024-08-06
Download on Hugging Face
Parameters10.9B
Context128K
Layers45
Architecturellama
Smallest quant2.6 GB
Quick answer

Llama 3.1 11b pretrained i1 needs about 8.6 GB of memory at Q4_K_M (a 6.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 2.6 GB (IQ1_S) to 8.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.0 GB.

Llama 3.1 11b pretrained i1 – a 10.9B parameter instruction model

Llama 3.1 11b pretrained i1 is a 10.9B parameter model trained on 131072 context tokens. It merges slices from two source models and is pretrained for one epoch on the Iambe dataset. The model is available in multiple GGUF quantizations.

Good at

  • Instruction following
  • Long‑context handling
  • Multilingual text generation

Limits

  • No vision support
  • License: llama3.1
  • Requires 8k context for memory estimates

Best for

  • Chatbots with 8k context
  • Text summarization
  • Code generation

Who it’s for. Developers needing a lightweight instruction model for local deployment. The model is suitable for users who prefer GGUF format and have GPU or CPU resources to run it.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.6 GB 4.6 GB
Fits Get file →
IQ1_M2.8 GB 4.8 GB
Fits Get file →
IQ2_XXS3.2 GB 5.2 GB
Fits Get file →
IQ2_XS3.4 GB 5.5 GB
Fits Get file →
IQ2_S3.6 GB 5.6 GB
Fits Get file →
IQ2_M3.9 GB 5.9 GB
Fits Get file →
Q2_K4.2 GB 6.2 GB
Fits Get file →
IQ3_XXS4.4 GB 6.4 GB
Fits Get file →
IQ3_XS4.7 GB 6.7 GB
Fits Get file →
Q3_K_S4.9 GB 6.9 GB
Fits Get file →
IQ3_S4.9 GB 6.9 GB
Fits Get file →
IQ3_M5.0 GB 7.1 GB
Fits Get file →
Q3_K_M5.4 GB 7.4 GB
Tight Get file →
Q3_K_L5.8 GB 7.8 GB
Tight Get file →
IQ4_XS6.0 GB 8.0 GB
Tight Get file →
Q4_06.3 GB 8.3 GB
Too big Get file →
Q4_K_S6.3 GB 8.3 GB
Too big Get file →
Q4_K_M6.6 GB 8.6 GB
Too big Get file →
Q5_K_S7.5 GB 9.6 GB
Too big Get file →
Q5_K_M7.7 GB 9.7 GB
Too big Get file →
Q6_K8.9 GB 10.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (4.6 GB memory at 8k context) or IQ1_M (4.8 GB). If 12 GB VRAM is available, Q4_K_M (8.6 GB) or Q5_K_M (9.7 GB) are options. Larger models like Q6_K require 10.9 GB memory at 8k context.

What GPU do you need for Llama 3.1 11b pretrained 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: the best quant that fits is IQ2_M (3.9 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ4_XS (6.0 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.9 GB file, about 10.9 GB in use).

Which Llama 3.1 11b pretrained i1 quant should you choose?

Q4_K_M is the usual starting point for Llama 3.1 11b pretrained i1: it balances file size and quality well. Here it is a 6.6 GB file.

If memory is tight, the smallest file is IQ1_S at 2.6 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
Parameters10.9B
Layers45
Trained context131,072 tokens
KV cache (fp16)180 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensellama3.1
Downloads (HF)639
Last updated2024-08-06

Frequently asked questions about Llama 3.1 11b pretrained i1

How much VRAM does Llama 3.1 11b pretrained i1 need?

About 8.6 GB at Q4_K_M with an 8K context window. That is the 6.6 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 Llama 3.1 11b pretrained i1 on an 8 GB GPU?

Yes, with IQ4_XS: the 6.0 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 Llama 3.1 11b pretrained i1 GGUF?

It depends on the quant: IQ1_S is 2.6 GB, IQ1_M is 2.8 GB, IQ2_XXS is 3.2 GB, IQ2_XS is 3.4 GB, IQ2_S is 3.6 GB, IQ2_M is 3.9 GB and 15 more.

What context length does Llama 3.1 11b pretrained 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 1.5 GB at 8K and 6.0 GB at 32K.

Where can I download Llama 3.1 11b pretrained i1 GGUF?

The files are on Hugging Face in the mradermacher/Llama-3.1-11b-pretrained-i1-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 Llama 3.1 11b pretrained i1 use?

Hugging Face lists the license as llama3.1. 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 this model on 8 GB VRAM?

Yes, the IQ1_S and IQ1_M quantizations use about 4.6–4.8 GB memory at 8k context, fitting within 8 GB VRAM.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is licensed under llama3.1.

Other GGUFs of Llama-3.1-11b-pretrained

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other medium models

All medium models →