PR

Prismatic 12b

PrismaticGGUF by bartowskiUpdated 2024-11-13
Download on Hugging Face
Parameters12.2B
Context128K
Layers40
Architecturellama
Smallest quant4.1 GB
Quick answer

Prismatic 12b needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 4.1 GB (IQ2_S) to 24.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Prismatic 12b – a 12.2 billion‑parameter Llama‑style model

Prismatic 12b is a 12.2 billion‑parameter model merged from Mistral‑Nemo‑Base‑2407, MN‑12B‑Mag‑Mell‑R1 and Mistral‑Nemo‑Prism‑12B‑v5. It supports a 131072‑token context window and is distributed in multiple GGUF quantizations.

Good at

  • Large context handling
  • Flexible quantization options
  • Mistral‑based architecture

Limits

  • No vision support
  • License not specified
  • Requires 8 k context for memory estimates

Best for

  • Chat applications needing long context
  • Fine‑tuning on custom data
  • Research on merged Llama models

Who it’s for. Developers and researchers who need a large‑context Llama‑style model with multiple quantization choices. The model is suitable for local inference using llama.cpp or LM Studio.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_S4.1 GB 6.0 GB
Fits Get file →
IQ2_M4.4 GB 6.3 GB
Fits Get file →
Q2_K4.8 GB 6.6 GB
Fits Get file →
IQ3_XS5.3 GB 7.1 GB
Fits Get file →
Q2_K_L5.4 GB 7.3 GB
Tight Get file →
Q3_K_S5.5 GB 7.4 GB
Tight Get file →
IQ3_M5.7 GB 7.6 GB
Tight Get file →
Q3_K_M6.1 GB 7.9 GB
Tight Get file →
Q3_K_L6.6 GB 8.4 GB
Too big Get file →
IQ4_XS6.7 GB 8.6 GB
Too big Get file →
Q4_07.1 GB 8.9 GB
Too big Get file →
Q4_07.1 GB 8.9 GB
Too big Get file →
Q4_07.1 GB 8.9 GB
Too big Get file →
Q4_07.1 GB 8.9 GB
Too big Get file →
Q4_K_S7.1 GB 9.0 GB
Too big Get file →
Q3_K_XL7.1 GB 9.0 GB
Too big Get file →
Q4_K_M7.5 GB 9.3 GB
Too big Get file →
Q4_K_L8.0 GB 9.8 GB
Too big Get file →
Q5_K_S8.5 GB 10.4 GB
Too big Get file →
Q5_K_M8.7 GB 10.6 GB
Too big Get file →
Q5_K_L9.1 GB 11.0 GB
Too big Get file →
Q6_K10.1 GB 11.9 GB
Too big Get file →
Q6_K_L10.4 GB 12.2 GB
Too big Get file →
Q8_013.0 GB 14.9 GB
Too big Get file →
F1624.5 GB 26.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 7.07 GB, memory 8.9 GB). For 12 GB VRAM, Q4_K_L (file size 7.98 GB, memory 9.8 GB) or Q5_K_M (file size 8.73 GB, memory 10.6 GB). For 16 GB VRAM, Q6_K (file size 10.06 GB, memory 11.9 GB) or Q6_K_L (file size 10.38 GB, memory 12.2 GB).

What GPU do you need for Prismatic 12b?

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 IQ2_S (4.1 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_M (6.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (24.5 GB file, about 26.3 GB in use).

Which Prismatic 12b quant should you choose?

Q4_K_M is the usual starting point for Prismatic 12b: it balances file size and quality well. Here it is a 7.5 GB file.

The Q8_0 file is 13.0 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 IQ2_S at 4.1 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

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

Source

Quantized bybartowski
FamilyPrismatic
Downloads (HF)1,398
Last updated2024-11-13

Frequently asked questions about Prismatic 12b

How much VRAM does Prismatic 12b need?

About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 Prismatic 12b on an 8 GB GPU?

Yes, with Q3_K_M: the 6.1 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 Prismatic 12b GGUF?

It depends on the quant: IQ2_S is 4.1 GB, IQ2_M is 4.4 GB, Q2_K is 4.8 GB, IQ3_XS is 5.3 GB, Q2_K_L is 5.4 GB, Q3_K_S is 5.5 GB and 19 more.

What context length does Prismatic 12b 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 Prismatic 12b GGUF?

The files are on Hugging Face in the bartowski/Prismatic-12b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Prismatic 12b on 8 GB VRAM?

Yes, a Q4_0 quant (7.07 GB) will fit and use about 8.9 GB of VRAM at 8 k context.

Does Prismatic 12b support vision tasks?

No, the model has no vision capabilities.

What prompt format does it use?

The model uses Mistral Tekken or ChatML format.

Other GGUFs of Prismatic-12b

Similar models

Browse all →

More from bartowski

All by bartowski →

More Prismatic models

All Prismatic →

Other medium models

All medium models →