AR

Arcee-Spark

ArceeGGUF by arcee-aiUpdated 2024-06-24
Download on Hugging Face
Parameters7.62B
Context32K
Layers28
Architectureqwen2
Smallest quant4.1 GB
Quick answer

Arcee-Spark needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 10 quants, from 4.1 GB (Q3_K_L) to 9.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Arcee-Spark is a 7.62B-parameter Arcee model in GGUF format, quantized by arcee-ai. Its trained context length is 32K tokens. The repository has 10 quant files, from 4.1 GB (Q3_K_L) to 9.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L4.1 GB 5.1 GB
Fits Get file →
IQ4_XS4.2 GB 5.2 GB
Fits Get file →
Q4_K_M4.7 GB 5.7 GB
Fits Get file →
Q5_K_M5.4 GB 6.4 GB
Fits Get file →
Q4_K_L6.1 GB 7.1 GB
Fits Get file →
Q6_K6.3 GB 7.2 GB
Tight Get file →
Q5_K_L6.8 GB 7.8 GB
Tight Get file →
Q6_K_L7.5 GB 8.5 GB
Too big Get file →
Q8_08.1 GB 9.1 GB
Too big Get file →
Q8_09.1 GB 10.1 GB
Too big Get file →

What GPU do you need for Arcee-Spark?

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 Q4_K_M (4.7 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_L (6.8 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.1 GB file, about 10.1 GB in use).

Which Arcee-Spark quant should you choose?

Q4_K_M is the usual starting point for Arcee-Spark: it balances file size and quality well. Here it is a 4.7 GB file.

The Q8_0 file is 8.1 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 Q3_K_L at 4.1 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

Architectureqwen2
Parameters7.62B
Layers28
Trained context32,768 tokens
KV cache (fp16)56 KB per token

Source

Quantized byarcee-ai
FamilyArcee
Licenseapache-2.0
Downloads (HF)189
Last updated2024-06-24

Frequently asked questions about Arcee-Spark

How much VRAM does Arcee-Spark need?

About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 Arcee-Spark on an 8 GB GPU?

Yes, with Q5_K_L: the 6.8 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Arcee-Spark GGUF?

It depends on the quant: Q3_K_L is 4.1 GB, IQ4_XS is 4.2 GB, Q4_K_M is 4.7 GB, Q5_K_M is 5.4 GB, Q4_K_L is 6.1 GB, Q6_K is 6.3 GB and 4 more.

What context length does Arcee-Spark support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download Arcee-Spark GGUF?

The files are on Hugging Face in the arcee-ai/Arcee-Spark-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 Arcee-Spark 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.

Similar models

Browse all →

More from arcee-ai

All by arcee-ai →

More Arcee models

All Arcee →

Other small models

All small models →