RY

Ryze Embed 2

RyzeGGUF by mradermacherUpdated 2024-08-10
Download on Hugging Face
Parameters13.2B
Context128K
Layers52
Architectureqwen2
Smallest quant5.1 GB
Quick answer

Ryze Embed 2 needs about 9.4 GB of memory at Q4_K_M (a 8.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 5.1 GB (Q2_K) to 14.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.

Ryze Embed 2 is a 13.2B-parameter Ryze model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 14 quant files, from 5.1 GB (Q2_K) to 14.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.1 GB 6.4 GB
Fits Get file →
IQ3_XS5.6 GB 7.0 GB
Fits Get file →
Q3_K_S5.9 GB 7.3 GB
Tight Get file →
IQ3_S5.9 GB 7.3 GB
Tight Get file →
IQ3_M6.1 GB 7.4 GB
Tight Get file →
Q3_K_M6.5 GB 7.9 GB
Tight Get file →
Q3_K_L7.0 GB 8.4 GB
Too big Get file →
IQ4_XS7.3 GB 8.6 GB
Too big Get file →
Q4_K_S7.6 GB 9.0 GB
Too big Get file →
Q4_K_M8.0 GB 9.4 GB
Too big Get file →
Q5_K_S9.2 GB 10.5 GB
Too big Get file →
Q5_K_M9.4 GB 10.8 GB
Too big Get file →
Q6_K10.8 GB 12.2 GB
Too big Get file →
Q8_014.0 GB 15.4 GB
Too big Get file →

What GPU do you need for Ryze Embed 2?

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: the best quant that fits is Q3_K_M (6.5 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (9.4 GB file, about 10.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (14.0 GB file, about 15.4 GB in use).

Which Ryze Embed 2 quant should you choose?

Q4_K_M is the usual starting point for Ryze Embed 2: it balances file size and quality well. Here it is a 8.0 GB file.

The Q8_0 file is 14.0 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 5.1 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

Architectureqwen2
Parameters13.2B
Layers52
Trained context131,072 tokens
KV cache (fp16)104 KB per token

Source

Quantized bymradermacher
FamilyRyze
Downloads (HF)166
Last updated2024-08-10

Frequently asked questions about Ryze Embed 2

How much VRAM does Ryze Embed 2 need?

About 9.4 GB at Q4_K_M with an 8K context window. That is the 8.0 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 Ryze Embed 2 on an 8 GB GPU?

Yes, with Q3_K_M: the 6.5 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ryze Embed 2 GGUF?

It depends on the quant: Q2_K is 5.1 GB, IQ3_XS is 5.6 GB, Q3_K_S is 5.9 GB, IQ3_S is 5.9 GB, IQ3_M is 6.1 GB, Q3_K_M is 6.5 GB and 8 more.

What context length does Ryze Embed 2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.5 GB at 32K.

Where can I download Ryze Embed 2 GGUF?

The files are on Hugging Face in the mradermacher/Ryze-Embed-2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Ryze models

All Ryze →

Other medium models

All medium models →