PH

Phi 3 medium 128k 10B lingyang v0.1 Q6 K

PhiGGUF by wwe180Updated 2024-05-21
Download on Hugging Face
Parameters10.6B
Context128K
Layers30
Architecturephi3
Smallest quant8.7 GB
Quick answer

Phi 3 medium 128k 10B lingyang v0.1 Q6 K needs about 10.4 GB of memory at Q6_K (a 8.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.0 GB.

Phi 3 medium 128k 10B lingyang v0.1 Q6 K is a 10.6B-parameter Phi model in GGUF format, quantized by wwe180. Its trained context length is 128K tokens. The repository has 1 quant file, from 8.7 GB (Q6_K) to 8.7 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K8.7 GB 10.4 GB
Too big Get file →

What GPU do you need for Phi 3 medium 128k 10B lingyang v0.1 Q6 K?

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: the best quant that fits is Q6_K (8.7 GB file, about 10.4 GB in use).

Which Phi 3 medium 128k 10B lingyang v0.1 Q6 K quant should you choose?

Q6_K (8.7 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephi3
Parameters10.6B
Layers30
Trained context131,072 tokens
KV cache (fp16)150 KB per token

Source

Quantized bywwe180
FamilyPhi
Downloads (HF)37
Last updated2024-05-21

Frequently asked questions about Phi 3 medium 128k 10B lingyang v0.1 Q6 K

How much VRAM does Phi 3 medium 128k 10B lingyang v0.1 Q6 K need?

About 10.4 GB at Q6_K with an 8K context window. That is the 8.7 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 Phi 3 medium 128k 10B lingyang v0.1 Q6 K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Phi 3 medium 128k 10B lingyang v0.1 Q6 K GGUF?

It depends on the quant: Q6_K is 8.7 GB.

What context length does Phi 3 medium 128k 10B lingyang v0.1 Q6 K support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.0 GB at 32K.

Where can I download Phi 3 medium 128k 10B lingyang v0.1 Q6 K GGUF?

The files are on Hugging Face in the wwe180/Phi-3-medium-128k-10B-lingyang-v0.1-Q6_K-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Phi-3-medium-128k-instruct

Similar models

Browse all →

More from wwe180

All by wwe180 →

More Phi models

All Phi →

Other medium models

All medium models →