LL

Llama-3-8B-Instruct-Gradient-1048k

LlamaGGUF by qwp4w3hybUpdated 2024-05-08
Download on Hugging Face
Parameters8.03B
Context1024K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

Llama-3-8B-Instruct-Gradient-1048k 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 19 quants, from 2.0 GB (IQ1_S) to 16.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Llama‑3‑8B‑Instruct‑Gradient‑1048k – 8B model with 1M+ token context

Llama‑3‑8B‑Instruct‑Gradient‑1048k extends the base Llama‑3‑8B to a context length of 1,048,576 tokens. It is trained on 830M tokens for this stage and 1.4B tokens total. The model is quantized for efficient inference with llama.cpp.

Good at

  • Long‑context reasoning
  • Instruct‑style dialogue
  • Retrieval‑augmented Q&A

Limits

  • No vision support
  • Requires special token 128009 in llama.cpp
  • License is other

Best for

  • Chatbots needing >1M token context
  • Custom agent development
  • Research on long‑context LLMs

Who it’s for. Developers building agents that must process very long documents or logs. Researchers exploring RoPE theta optimization for extended context. Teams needing a 8B model with minimal training for long‑context tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.0 GB 3.6 GB
Fits Get file →
IQ2_XXS2.4 GB 4.0 GB
Fits Get file →
IQ2_XS2.6 GB 4.2 GB
Fits Get file →
IQ2_S2.8 GB 4.3 GB
Fits Get file →
IQ2_M2.9 GB 4.5 GB
Fits Get file →
IQ3_XXS3.3 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
IQ4_XS4.4 GB 6.0 GB
Fits Get file →
Q4_04.7 GB 6.2 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 8 GB VRAM use IQ2_XXS or IQ2_XS (est. 4 GB memory). With 12 GB VRAM, Q4_K_M or Q5_K_S are suitable (6.5 GB or 7.2 GB memory). For 24 GB VRAM, Q6_K or Q8_0 provide higher precision (8.2 GB or 10.1 GB memory).

What GPU do you need for Llama-3-8B-Instruct-Gradient-1048k?

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_XXS (2.4 GB file, about 4.0 GB in use).
  • 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 Llama-3-8B-Instruct-Gradient-1048k quant should you choose?

Q4_K_M is the usual starting point for Llama-3-8B-Instruct-Gradient-1048k: 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 IQ1_S at 2.0 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 context1,048,576 tokens
KV cache (fp16)128 KB per token

Source

Quantized byqwp4w3hyb
FamilyLlama
Licenseother
Downloads (HF)739
Last updated2024-05-08

Frequently asked questions about Llama-3-8B-Instruct-Gradient-1048k

How much VRAM does Llama-3-8B-Instruct-Gradient-1048k 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 Llama-3-8B-Instruct-Gradient-1048k 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 Llama-3-8B-Instruct-Gradient-1048k GGUF?

It depends on the quant: IQ1_S is 2.0 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB, IQ2_M is 2.9 GB, IQ3_XXS is 3.3 GB and 13 more.

What context length does Llama-3-8B-Instruct-Gradient-1048k support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). 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 Llama-3-8B-Instruct-Gradient-1048k GGUF?

The files are on Hugging Face in the qwp4w3hyb/Llama-3-8B-Instruct-Gradient-1048k-iMat-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-3-8B-Instruct-Gradient-1048k use?

Hugging Face lists the license as other. 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 IQ2_XXS or IQ2_XS quantizations, which estimate 4 GB memory at 8k context.

Does this model support vision?

No, the model has no vision capability.

What special token is required for llama.cpp?

Add token 128009 to the tokenizer for instruct mode.

Other GGUFs of Llama-3-8B-Instruct-Gradient-1048k

Similar models

Browse all →

More from qwp4w3hyb

All by qwp4w3hyb →

More Llama models

All Llama →

Other small models

All small models →