OP

OpenCrystal Instruct 128k

OpencrystalGGUF by mradermacherUpdated 2024-08-16
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant4.8 GB
Quick answer

OpenCrystal Instruct 128k 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 14 quants, from 4.8 GB (Q2_K) to 13.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

OpenCrystal Instruct 128k – 12.2B llama architecture

OpenCrystal Instruct 128k is a 12.2 billion parameter llama model trained on 1,024,000 context tokens. It is available in multiple GGUF quantizations ranging from Q2_K to Q8_0. The model supports instruction following and large context handling.

Good at

  • Instruction following
  • Large context (128k tokens)
  • Multi‑part quant support

Limits

  • No vision support
  • License not specified
  • Large memory requirement for higher quants

Best for

  • Chatbots needing long context
  • Document summarization
  • Code generation

Who it’s for. Developers and researchers who need a large‑context instruction model in GGUF format. Suitable for local deployment with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.8 GB 6.6 GB
Fits Get file →
IQ3_XS5.3 GB 7.1 GB
Fits Get file →
Q3_K_S5.5 GB 7.4 GB
Tight Get file →
IQ3_S5.6 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_XS6.8 GB 8.6 GB
Too big Get file →
Q4_K_S7.1 GB 9.0 GB
Too big Get file →
Q4_K_M7.5 GB 9.3 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 →
Q6_K10.1 GB 11.9 GB
Too big Get file →
Q8_013.0 GB 14.9 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (7.9 GB estimate). For 12 GB VRAM use Q5_K_M (10.6 GB estimate). For 16 GB VRAM use Q6_K (11.9 GB estimate).

What GPU do you need for OpenCrystal Instruct 128k?

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: 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).

Which OpenCrystal Instruct 128k quant should you choose?

Q4_K_M is the usual starting point for OpenCrystal Instruct 128k: 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 Q2_K at 4.8 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
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized bymradermacher
Downloads (HF)623
Last updated2024-08-16

Frequently asked questions about OpenCrystal Instruct 128k

How much VRAM does OpenCrystal Instruct 128k 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 OpenCrystal Instruct 128k 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 OpenCrystal Instruct 128k GGUF?

It depends on the quant: Q2_K is 4.8 GB, IQ3_XS is 5.3 GB, Q3_K_S is 5.5 GB, IQ3_S is 5.6 GB, IQ3_M is 5.7 GB, Q3_K_M is 6.1 GB and 8 more.

What context length does OpenCrystal Instruct 128k support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). 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 OpenCrystal Instruct 128k GGUF?

The files are on Hugging Face in the mradermacher/OpenCrystal-Instruct-128k-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 Q4_K_M on 8 GB VRAM?

Yes, Q4_K_M estimates 9.3 GB at 8k context, which is within 8 GB VRAM with some overhead.

Is there a quant with the smallest file size?

Q2_K is the smallest at 4.79 GB, but it has the highest memory estimate of 6.6 GB at 8k context.

Does the model support vision?

No, the model does not support vision capabilities.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Opencrystal models

All Opencrystal →

Other medium models

All medium models →