LL

namespace Pt Llama 3 8B Instruct 80K QLoRA Merged

LlamaGGUF by RichardErkhovUpdated 2024-08-20
Download on Hugging Face
Parameters8.03B
Context80K
Layers32
Architecturellama
Smallest quant3.2 GB
Quick answer

namespace Pt Llama 3 8B Instruct 80K QLoRA Merged 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.

Namespace Pt Llama 3 8B Instruct 80K QLoRA Merged – extended context, compact quantizations

Namespace Pt Llama 3 8B Instruct 80K QLoRA Merged extends the original Llama‑3‑8B‑Instruct to 80K context tokens using QLoRA. The model is released under the MIT license and is available in multiple GGUF quantizations. It is suitable for long‑context text generation tasks.

Good at

  • Long‑context generation up to 80K tokens
  • Efficient inference with low‑bit quantizations
  • Stable performance on text‑generation benchmarks

Limits

  • No vision or multimodal support
  • Requires 8K context for accurate inference
  • Large memory for higher‑bit quantizations

Best for

  • Document summarization with long context
  • Code generation from large codebases
  • Research on long‑context evaluation benchmarks

Who it’s for. Developers and researchers needing a compact, long‑context Llama‑3 model. The model is free to use under the MIT license and can be run locally with llama.cpp.

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 8GB VRAM, use Q4_0 or Q4_K (file size 4.66 GB, memory 6.2 GB). For 12GB VRAM, Q5_0 or Q5_K (file size 5.6 GB, memory 7.2 GB) offers a good balance. For 24GB VRAM, Q6_K (file size 6.6 GB, memory 8.2 GB) or Q8_0 (file size 8.54 GB, memory 10.1 GB) provide higher precision.

What GPU do you need for namespace Pt Llama 3 8B Instruct 80K QLoRA Merged?

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 namespace Pt Llama 3 8B Instruct 80K QLoRA Merged quant should you choose?

Q4_K_M is the usual starting point for namespace Pt Llama 3 8B Instruct 80K QLoRA Merged: 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 context81,920 tokens
KV cache (fp16)128 KB per token

Source

Quantized byRichardErkhov
FamilyLlama
Licensemit
Downloads (HF)604
Last updated2024-08-20

Frequently asked questions about namespace Pt Llama 3 8B Instruct 80K QLoRA Merged

How much VRAM does namespace Pt Llama 3 8B Instruct 80K QLoRA Merged 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 namespace Pt Llama 3 8B Instruct 80K QLoRA Merged 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 namespace Pt Llama 3 8B Instruct 80K QLoRA Merged 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 namespace Pt Llama 3 8B Instruct 80K QLoRA Merged support?

The GGUF header lists a trained context length of 81,920 tokens (80K). 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 namespace Pt Llama 3 8B Instruct 80K QLoRA Merged GGUF?

The files are on Hugging Face in the RichardErkhov/namespace-Pt_-_Llama-3-8B-Instruct-80K-QLoRA-Merged-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 namespace Pt Llama 3 8B Instruct 80K QLoRA Merged use?

Hugging Face lists the license as mit. 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, using Q4_0 or Q4_K quantizations which require about 6.2 GB of VRAM at 8K context.

Does this model support vision or multimodal inputs?

No, it is a text‑only model with no vision capabilities.

What license applies to this model?

The model is released under the MIT license, allowing free use and modification.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Llama models

All Llama →

Other small models

All small models →