LL

vicgalle Configurable Llama 3.1 8B Instruct

LlamaGGUF by RichardErkhovUpdated 2024-08-05
Download on Hugging Face
Parameters8.03B
Context128K
Layers32
Architecturellama
Smallest quant3.2 GB
Quick answer

vicgalle Configurable Llama 3.1 8B Instruct needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 22 quants, from 3.2 GB (Q2_K) to 8.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Configurable Llama‑3.1 8B Instruct for safe or uncensored use

This 8.03‑billion‑parameter Llama‑3.1 model is fine‑tuned with configurable safety tuning. It supports multiple system prompts for safe, uncensored, or role‑play behavior. The model is released under the apache‑2.0 license.

Good at

  • Safe or uncensored instruction following
  • Configurable system prompts
  • Large context of 131072 tokens

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • License is apache‑2.0

Best for

  • Research on safety alignment
  • Custom prompt engineering
  • Educational demos

Who it’s for. Researchers and developers needing a flexible Llama‑3.1 base that can be toggled between safe and uncensored modes. The model is suitable for academic studies and prototype applications where safety configuration is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.2 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K4.0 GB 5.6 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.5 GB 6.1 GB
Fits Get file →
Q4_04.7 GB 6.2 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
IQ4_NL4.7 GB 6.3 GB
Fits Get file →
Q4_K4.9 GB 6.5 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q4_15.1 GB 6.7 GB
Fits Get file →
Q5_05.6 GB 7.2 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K5.7 GB 7.3 GB
Tight Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q5_16.1 GB 7.6 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →

For 8‑GB VRAM, use Q4_0 (file size 4.66 GB, estimated 6.2 GB memory). For 12‑GB VRAM, Q5_0 (5.6 GB, 7.2 GB memory) or Q5_K (5.73 GB, 7.3 GB memory) are suitable. For 16‑GB VRAM, Q6_K (6.6 GB, 8.2 GB memory) or Q8_0 (8.54 GB, 10.1 GB memory) provide higher precision.

What GPU do you need for vicgalle Configurable Llama 3.1 8B Instruct?

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 Q3_K_L (4.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_1 (6.1 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).

Which vicgalle Configurable Llama 3.1 8B Instruct quant should you choose?

Q4_K_M is the usual starting point for vicgalle Configurable Llama 3.1 8B Instruct: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 GB, about 1.7 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 3.2 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
Parameters8.03B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byRichardErkhov
FamilyLlama
Licenseapache-2.0
Downloads (HF)867
Last updated2024-08-05

Frequently asked questions about vicgalle Configurable Llama 3.1 8B Instruct

How much VRAM does vicgalle Configurable Llama 3.1 8B Instruct need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 vicgalle Configurable Llama 3.1 8B Instruct on an 8 GB GPU?

Yes, with Q5_1: the 6.1 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of vicgalle Configurable Llama 3.1 8B Instruct GGUF?

It depends on the quant: Q2_K is 3.2 GB, IQ3_XS is 3.5 GB, Q3_K_S is 3.7 GB, IQ3_S is 3.7 GB, IQ3_M is 3.8 GB, Q3_K is 4.0 GB and 16 more.

What context length does vicgalle Configurable Llama 3.1 8B Instruct support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download vicgalle Configurable Llama 3.1 8B Instruct GGUF?

The files are on Hugging Face in the RichardErkhov/vicgalle_-_Configurable-Llama-3.1-8B-Instruct-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 vicgalle Configurable Llama 3.1 8B Instruct 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, the Q4_0 quantization requires about 6.2 GB of VRAM at 8‑k context, which fits within 8 GB.

Does this model support vision?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Llama models

All Llama →

Other small models

All small models →