LL

Reflection Llama 3.1 70B

LlamaGGUF by jhofsethUpdated 2024-09-13
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant27.5 GB
Quick answer

Reflection Llama 3.1 70B needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 27.5 GB (IQ3_XXS) to 141.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Reflection Llama 3.1 70B is a 70.6B-parameter Llama model in GGUF format, quantized by jhofseth. Its trained context length is 128K tokens. The repository has 10 quant files, from 27.5 GB (IQ3_XXS) to 141.1 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS27.5 GB 30.7 GB
Too big Get file →
IQ3_XS29.3 GB 32.5 GB
Too big Get file →
IQ4_XS37.9 GB 41.1 GB
Too big Get file →
IQ4_NL40.1 GB 43.2 GB
Too big Get file →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →
Q6_K57.9 GB (2 parts) 61.1 GB
Too big Get file →
Q8_075.0 GB (2 parts) 78.2 GB
Too big Get file →
—141.1 GB (6 parts) 144.3 GB
Too big Get file →

What GPU do you need for Reflection Llama 3.1 70B?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ3_XXS (27.5 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 45.7 GB in use).

Which Reflection Llama 3.1 70B quant should you choose?

Q4_K_M is the usual starting point for Reflection Llama 3.1 70B: it balances file size and quality well. Here it is a 42.5 GB file.

The Q8_0 file is 75.0 GB, about 1.8 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 27.5 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
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized byjhofseth
FamilyLlama
Licensellama3
Downloads (HF)212
Last updated2024-09-13

Frequently asked questions about Reflection Llama 3.1 70B

How much VRAM does Reflection Llama 3.1 70B need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 Reflection Llama 3.1 70B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 30.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Reflection Llama 3.1 70B GGUF?

It depends on the quant: IQ3_XXS is 27.5 GB, IQ3_XS is 29.3 GB, IQ4_XS is 37.9 GB, IQ4_NL is 40.1 GB, Q4_K_S is 40.3 GB, Q4_K_M is 42.5 GB and 4 more.

What context length does Reflection Llama 3.1 70B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Reflection Llama 3.1 70B GGUF?

The files are on Hugging Face in the jhofseth/Reflection-Llama-3.1-70B-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 Reflection Llama 3.1 70B use?

Hugging Face lists the license as llama3. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of ref_70_e3

Similar models

Browse all →

More Llama models

All Llama →

Other large models

All large models →