LL

Llama 3.1 8B Pruned 4 Layers LoRA PEFT 3.0 i1

LlamaGGUF by mradermacherUpdated 2024-08-09
Download on Hugging Face
Parameters6.94B
Context128K
Layers27
Architecturellama
Smallest quant1.8 GB
Quick answer

Llama 3.1 8B Pruned 4 Layers LoRA PEFT 3.0 i1 needs about 5.7 GB of memory at Q4_K_M (a 4.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 21 quants, from 1.8 GB (IQ1_S) to 5.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.6 GB.

Llama 3.1 8B Pruned 4 Layers LoRA PEFT 3.0 i1 – lightweight, tool‑aware LLM

This model is a 6.94B‑parameter Llama 3.1 variant that has been pruned and fine‑tuned with LoRA PEFT. It supports tool usage and is released under the apache‑2.0 license. The model was trained on 131072 context tokens.

Good at

  • Tool‑integrated reasoning
  • Efficient inference on modest hardware
  • Fine‑tuned for specific tasks

Limits

  • No vision support
  • Requires 131072 token context
  • Memory usage depends on quant

Best for

  • Chatbots needing tool calls
  • Rapid prototyping of LLM applications
  • Deployments on edge devices

Who it’s for. Developers and researchers who need a smaller, faster Llama 3.1 model with tool support. The model is suitable for local deployment where GPU memory is limited.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.8 GB 3.2 GB
Fits Get file →
IQ1_M1.9 GB 3.3 GB
Fits Get file →
IQ2_XXS2.1 GB 3.5 GB
Fits Get file →
IQ2_XS2.3 GB 3.7 GB
Fits Get file →
IQ2_S2.4 GB 3.8 GB
Fits Get file →
IQ2_M2.6 GB 4.0 GB
Fits Get file →
Q2_K2.8 GB 4.2 GB
Fits Get file →
IQ3_XXS2.9 GB 4.3 GB
Fits Get file →
IQ3_XS3.1 GB 4.5 GB
Fits Get file →
Q3_K_S3.2 GB 4.6 GB
Fits Get file →
IQ3_S3.2 GB 4.6 GB
Fits Get file →
IQ3_M3.3 GB 4.7 GB
Fits Get file →
Q3_K_M3.5 GB 4.9 GB
Fits Get file →
Q3_K_L3.8 GB 5.2 GB
Fits Get file →
IQ4_XS3.9 GB 5.3 GB
Fits Get file →
Q4_04.1 GB 5.5 GB
Fits Get file →
Q4_K_S4.1 GB 5.5 GB
Fits Get file →
Q4_K_M4.3 GB 5.7 GB
Fits Get file →
Q5_K_S4.8 GB 6.3 GB
Fits Get file →
Q5_K_M5.0 GB 6.4 GB
Fits Get file →
Q6_K5.7 GB 7.1 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S (1.79 GB, 3.2 GB memory at 8 k context) or IQ1_M (1.91 GB, 3.3 GB). For 12 GB VRAM, IQ2_M (2.58 GB, 4 GB) or Q2_K (2.78 GB, 4.2 GB) are good choices. For 16 GB VRAM, Q3_K_M (3.49 GB, 4.9 GB) or Q4_K_M (4.26 GB, 5.7 GB) provide higher quality.

What GPU do you need for Llama 3.1 8B Pruned 4 Layers LoRA PEFT 3.0 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: the best quant that fits is IQ2_M (2.6 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.3 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.7 GB file, about 7.1 GB in use).

Which Llama 3.1 8B Pruned 4 Layers LoRA PEFT 3.0 i1 quant should you choose?

Q4_K_M is the usual starting point for Llama 3.1 8B Pruned 4 Layers LoRA PEFT 3.0 i1: it balances file size and quality well. Here it is a 4.3 GB file.

If memory is tight, the smallest file is IQ1_S at 1.8 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
Parameters6.94B
Layers27
Trained context131,072 tokens
KV cache (fp16)108 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licenseapache-2.0
Downloads (HF)1,405
Last updated2024-08-09

Frequently asked questions about Llama 3.1 8B Pruned 4 Layers LoRA PEFT 3.0 i1

How much VRAM does Llama 3.1 8B Pruned 4 Layers LoRA PEFT 3.0 i1 need?

About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.3 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 8B Pruned 4 Layers LoRA PEFT 3.0 i1 on an 8 GB GPU?

Yes, with Q6_K: the 5.7 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 3.1 8B Pruned 4 Layers LoRA PEFT 3.0 i1 GGUF?

It depends on the quant: IQ1_S is 1.8 GB, IQ1_M is 1.9 GB, IQ2_XXS is 2.1 GB, IQ2_XS is 2.3 GB, IQ2_S is 2.4 GB, IQ2_M is 2.6 GB and 15 more.

What context length does Llama 3.1 8B Pruned 4 Layers LoRA PEFT 3.0 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 0.9 GB at 8K and 3.6 GB at 32K.

Where can I download Llama 3.1 8B Pruned 4 Layers LoRA PEFT 3.0 i1 GGUF?

The files are on Hugging Face in the mradermacher/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-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 8B Pruned 4 Layers LoRA PEFT 3.0 i1 use?

Hugging Face lists the license as apache-2.0. 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, use IQ1_S or IQ1_M quant files. They require about 3.2–3.3 GB of VRAM at 8 k context.

Does this model support image input?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →