MA

MagpieLM 4B SFT v0.1 Q6 K

MagpielmGGUF by ijohn07Updated 2024-09-18
Download on Hugging Face
Parameters4.51B
Context128K
Layers32
Architecturellama
Smallest quant3.7 GB
Quick answer

MagpieLM 4B SFT v0.1 Q6 K needs about 5.3 GB of memory at Q6_K (a 3.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

MagpieLM 4B SFT v0.1 Q6 K is a 4.51B-parameter Magpielm model in GGUF format, quantized by ijohn07. Its trained context length is 128K tokens. The repository has 1 quant file, from 3.7 GB (Q6_K) to 3.7 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K3.7 GB 5.3 GB
Fits Get file →

What GPU do you need for MagpieLM 4B SFT 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: the best quant that fits is Q6_K (3.7 GB file, about 5.3 GB in use).

Which MagpieLM 4B SFT v0.1 Q6 K quant should you choose?

Q6_K (3.7 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

Architecturellama
Parameters4.51B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byijohn07
FamilyMagpielm
Downloads (HF)17
Last updated2024-09-18

Frequently asked questions about MagpieLM 4B SFT v0.1 Q6 K

How much VRAM does MagpieLM 4B SFT v0.1 Q6 K need?

About 5.3 GB at Q6_K with an 8K context window. That is the 3.7 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 MagpieLM 4B SFT v0.1 Q6 K on an 8 GB GPU?

Yes, with Q6_K: the 3.7 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MagpieLM 4B SFT v0.1 Q6 K GGUF?

It depends on the quant: Q6_K is 3.7 GB.

What context length does MagpieLM 4B SFT 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 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download MagpieLM 4B SFT v0.1 Q6 K GGUF?

The files are on Hugging Face in the ijohn07/MagpieLM-4B-SFT-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 MagpieLM-4B-SFT-v0.1

Similar models

Browse all →

More from ijohn07

All by ijohn07 →

More Magpielm models

All Magpielm →

Other small models

All small models →