PR

MN Prismatic 12b Q5 K M

PrismaticGGUF by SaisExperimentsUpdated 2024-11-13
Download on Hugging Face
Parameters12.2B
Context128K
Layers40
Architecturellama
Smallest quant8.7 GB
Quick answer

MN Prismatic 12b Q5 K M needs about 10.6 GB of memory at Q5_K_M (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 5.4 GB.

MN Prismatic 12b Q5 K M is a 12.2B-parameter Prismatic model in GGUF format, quantized by SaisExperiments. Its trained context length is 128K tokens. The repository has 1 quant file, from 8.7 GB (Q5_K_M) to 8.7 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M8.7 GB 10.6 GB
Too big Get file →

What GPU do you need for MN Prismatic 12b Q5 K M?

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 Q5_K_M (8.7 GB file, about 10.6 GB in use).

Which MN Prismatic 12b Q5 K M quant should you choose?

Q5_K_M (8.7 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters12.2B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized bySaisExperiments
FamilyPrismatic
Downloads (HF)14
Last updated2024-11-13

Frequently asked questions about MN Prismatic 12b Q5 K M

How much VRAM does MN Prismatic 12b Q5 K M need?

About 10.6 GB at Q5_K_M 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 MN Prismatic 12b Q5 K M on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MN Prismatic 12b Q5 K M GGUF?

It depends on the quant: Q5_K_M is 8.7 GB.

What context length does MN Prismatic 12b Q5 K M 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 5.4 GB at 32K.

Where can I download MN Prismatic 12b Q5 K M GGUF?

The files are on Hugging Face in the SaisExperiments/MN-Prismatic-12b-Q5_K_M-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 Prismatic-12b

Similar models

Browse all →

More from SaisExperiments

All by SaisExperiments →

More Prismatic models

All Prismatic →

Other medium models

All medium models →