AR

ArrowPro-7B-KillerWhale

ArrowproGGUF by mmngaUpdated 2024-05-29
Download on Hugging Face
Parameters7.24B
Context4K
Layers32
Architecturellama
Smallest quant1.6 GB
Quick answer

ArrowPro-7B-KillerWhale needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.6 GB (IQ1_S) to 7.7 GB (Q8_0).

ArrowPro-7B-KillerWhale – 7.24B llama model in GGUF format

ArrowPro-7B-KillerWhale is a 7.24B parameter llama architecture model. It is available in multiple quantizations from IQ1_S to Q8_0. The model supports a 4096 token context window and is released under the apache-2.0 license.

Good at

  • Large context handling
  • Flexible quantization options
  • Open-source licensing

Limits

  • No vision capabilities
  • No mixture of experts
  • Limited language metadata

Best for

  • Chatbots requiring 4096 token context
  • Local inference on mid-range GPUs
  • Educational demonstrations of llama models

Who it’s for. Developers and researchers who need a 7B llama model with a 4096 token context window and flexible quantization. The model is suitable for local deployment on systems with moderate VRAM and for educational purposes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 2.6 GB
Fits Get file →
IQ1_M1.8 GB 2.8 GB
Fits Get file →
IQ2_XXS2.0 GB 3.0 GB
Fits Get file →
IQ2_XS2.2 GB 3.2 GB
Fits Get file →
IQ2_S2.3 GB 3.3 GB
Fits Get file →
IQ2_M2.5 GB 3.5 GB
Fits Get file →
Q2_K2.7 GB 3.8 GB
Fits Get file →
IQ3_XXS2.8 GB 3.9 GB
Fits Get file →
IQ3_XS3.0 GB 4.1 GB
Fits Get file →
Q3_K_S3.2 GB 4.2 GB
Fits Get file →
IQ3_S3.2 GB 4.2 GB
Fits Get file →
IQ3_M3.3 GB 4.3 GB
Fits Get file →
Q3_K_M3.5 GB 4.6 GB
Fits Get file →
Q3_K_L3.8 GB 4.9 GB
Fits Get file →
IQ4_XS3.9 GB 4.9 GB
Fits Get file →
Q4_04.1 GB 5.1 GB
Fits Get file →
IQ4_NL4.1 GB 5.2 GB
Fits Get file →
Q4_K_S4.1 GB 5.2 GB
Fits Get file →
Q4_K_M4.4 GB 5.4 GB
Fits Get file →
Q5_05.0 GB 6.0 GB
Fits Get file →
Q5_K_S5.0 GB 6.0 GB
Fits Get file →
Q5_K_M5.1 GB 6.2 GB
Fits Get file →
Q6_K5.9 GB 7.0 GB
Fits Get file →
Q8_07.7 GB 8.7 GB
Too big Get file →

For 8 GB VRAM, use IQ2_S (est. 3.9 GB) or Q3_K_S (est. 4.7 GB). For 12 GB VRAM, Q4_K_M (est. 5.9 GB) or Q5_K_M (est. 6.7 GB) are suitable. For 16 GB VRAM, Q6_K (est. 7.5 GB) or Q8_0 (est. 9.3 GB) provide higher precision.

What GPU do you need for ArrowPro-7B-KillerWhale?

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_S (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).

Which ArrowPro-7B-KillerWhale quant should you choose?

Q4_K_M is the usual starting point for ArrowPro-7B-KillerWhale: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 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 IQ1_S at 1.6 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
Parameters7.24B
Layers32
Trained context4,096 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymmnga
FamilyArrowpro
Licenseapache-2.0
Downloads (HF)2,670
Last updated2024-05-29

Frequently asked questions about ArrowPro-7B-KillerWhale

How much VRAM does ArrowPro-7B-KillerWhale need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 ArrowPro-7B-KillerWhale on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ArrowPro-7B-KillerWhale GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.3 GB, IQ2_M is 2.5 GB and 18 more.

What context length does ArrowPro-7B-KillerWhale support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.

Where can I download ArrowPro-7B-KillerWhale GGUF?

The files are on Hugging Face in the mmnga/ArrowPro-7B-KillerWhale-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 ArrowPro-7B-KillerWhale 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 ArrowPro-7B-KillerWhale on 8 GB VRAM?

Yes, use IQ2_S or Q3_K_S quantizations, which estimate 3.9 GB and 4.7 GB of VRAM at 8k context.

Does this model support vision tasks?

No, ArrowPro-7B-KillerWhale is a text-only model with 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 mmnga

All by mmnga →

More Arrowpro models

All Arrowpro →

Other small models

All small models →