LL

SOVL_Llama3_8B

LlamaGGUF by LewdiculousUpdated 2024-05-04
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant3.3 GB
Quick answer

SOVL_Llama3_8B 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 11 quants, from 3.3 GB (IQ3_XXS) to 16.1 GB (F16).

SOVL_Llama3_8B – 8.03B parameter Llama model in GGUF format

SOVL_Llama3_8B is an 8.03B parameter Llama model quantized for efficient inference. It supports a 8192 token context window and is distributed under the apache-2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Efficient inference on modest GPUs
  • Large context handling
  • Stable performance with llama.cpp

Limits

  • No vision support
  • Requires at least 8GB VRAM for higher quality quants
  • No mixture of experts

Best for

  • Chatbot deployments
  • Text generation tasks
  • Rapid prototyping

Who it’s for. Developers and researchers needing a balance between model size and inference speed. Suitable for local deployment on consumer GPUs with 8GB VRAM or more.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS3.3 GB 4.8 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
IQ4_XS4.4 GB 6.0 GB
Fits Get file →
IQ4_NL4.7 GB 6.3 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 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 →
F1616.1 GB 17.6 GB
Too big Get file →

For 8GB VRAM GPUs, use the Q4_K_M quant (file size 4.92GB, estimated memory 6.5GB at 8k context). If more VRAM is available, Q5_K_M (5.73GB, 7.3GB) or Q6_K (6.6GB, 8.2GB) offer higher quality. Lower‑bit quants like IQ3_XXS (3.27GB, 4.8GB) fit tighter memory budgets.

What GPU do you need for SOVL_Llama3_8B?

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 IQ4_XS (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).

Which SOVL_Llama3_8B quant should you choose?

Q4_K_M is the usual starting point for SOVL_Llama3_8B: 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 IQ3_XXS at 3.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byLewdiculous
FamilyLlama
Licenseapache-2.0
Downloads (HF)635
Last updated2024-05-04

Frequently asked questions about SOVL_Llama3_8B

How much VRAM does SOVL_Llama3_8B 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 SOVL_Llama3_8B on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SOVL_Llama3_8B GGUF?

It depends on the quant: IQ3_XXS is 3.3 GB, IQ3_M is 3.8 GB, IQ4_XS is 4.4 GB, IQ4_NL is 4.7 GB, Q4_K_S is 4.7 GB, Q4_K_M is 4.9 GB and 5 more.

What context length does SOVL_Llama3_8B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download SOVL_Llama3_8B GGUF?

The files are on Hugging Face in the Lewdiculous/SOVL_Llama3_8B-GGUF-IQ-Imatrix repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does SOVL_Llama3_8B 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 an 8GB VRAM GPU?

Yes, the Q4_K_M quant uses approximately 6.5GB of VRAM at 8k context, fitting within an 8GB GPU. Lower quants also fit if needed.

What context length is supported?

The model was trained with 8192 tokens and supports up to that context length in inference.

Is there a license restriction?

The model is released under the apache-2.0 license, allowing free use and modification.

Similar models

Browse all →

More from Lewdiculous

All by Lewdiculous →

More Llama models

All Llama →

Other small models

All small models →