OP

OpenCrystal 12B L3 i1

OpencrystalGGUF by mradermacherUpdated 2024-09-08
Download on Hugging Face
Parameters11.5B
Context8K
Layers48
Architecturellama
Smallest quant2.8 GB
Quick answer

OpenCrystal 12B L3 i1 needs about 9.1 GB of memory at Q4_K_M (a 7.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 2.8 GB (IQ1_S) to 9.5 GB (Q6_K).

OpenCrystal 12B L3 i1 is a 11.5B-parameter Opencrystal model in GGUF format, quantized by mradermacher. Its trained context length is 8K tokens. The repository has 21 quant files, from 2.8 GB (IQ1_S) to 9.5 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.8 GB 4.9 GB
Fits Get file →
IQ1_M3.0 GB 5.1 GB
Fits Get file →
IQ2_XXS3.3 GB 5.4 GB
Fits Get file →
IQ2_XS3.6 GB 5.7 GB
Fits Get file →
IQ2_S3.8 GB 6.0 GB
Fits Get file →
IQ2_M4.1 GB 6.2 GB
Fits Get file →
Q2_K4.5 GB 6.6 GB
Fits Get file →
IQ3_XXS4.6 GB 6.7 GB
Fits Get file →
IQ3_XS4.9 GB 7.1 GB
Fits Get file →
Q3_K_S5.2 GB 7.3 GB
Tight Get file →
IQ3_S5.2 GB 7.3 GB
Tight Get file →
IQ3_M5.3 GB 7.5 GB
Tight Get file →
Q3_K_M5.7 GB 7.8 GB
Tight Get file →
Q3_K_L6.2 GB 8.3 GB
Too big Get file →
IQ4_XS6.3 GB 8.4 GB
Too big Get file →
Q4_06.6 GB 8.8 GB
Too big Get file →
Q4_K_S6.7 GB 8.8 GB
Too big Get file →
Q4_K_M7.0 GB 9.1 GB
Too big Get file →
Q5_K_S8.0 GB 10.1 GB
Too big Get file →
Q5_K_M8.2 GB 10.3 GB
Too big Get file →
Q6_K9.5 GB 11.6 GB
Too big Get file →

What GPU do you need for OpenCrystal 12B L3 i1?

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 (3.8 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_M (5.7 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (9.5 GB file, about 11.6 GB in use).

Which OpenCrystal 12B L3 i1 quant should you choose?

Q4_K_M is the usual starting point for OpenCrystal 12B L3 i1: it balances file size and quality well. Here it is a 7.0 GB file.

If memory is tight, the smallest file is IQ1_S at 2.8 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
Parameters11.5B
Layers48
Trained context8,192 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
Downloads (HF)157
Last updated2024-09-08

Frequently asked questions about OpenCrystal 12B L3 i1

How much VRAM does OpenCrystal 12B L3 i1 need?

About 9.1 GB at Q4_K_M with an 8K context window. That is the 7.0 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 OpenCrystal 12B L3 i1 on an 8 GB GPU?

Yes, with Q3_K_M: the 5.7 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of OpenCrystal 12B L3 i1 GGUF?

It depends on the quant: IQ1_S is 2.8 GB, IQ1_M is 3.0 GB, IQ2_XXS is 3.3 GB, IQ2_XS is 3.6 GB, IQ2_S is 3.8 GB, IQ2_M is 4.1 GB and 15 more.

What context length does OpenCrystal 12B L3 i1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.6 GB at 8K.

Where can I download OpenCrystal 12B L3 i1 GGUF?

The files are on Hugging Face in the mradermacher/OpenCrystal-12B-L3-i1-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 OpenCrystal-12B-L3

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Opencrystal models

All Opencrystal →

Other medium models

All medium models →