DA

Darkknight535 OpenCrystal 15B L3 v3

DarkknightGGUF by RichardErkhovUpdated 2024-09-18
Download on Hugging Face
Parameters15B
Context8K
Layers64
Architecturellama
Smallest quant5.7 GB
Quick answer

Darkknight535 OpenCrystal 15B L3 v3 needs about 11.8 GB of memory at Q4_K_M (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 22 quants, from 5.7 GB (Q2_K) to 16.0 GB (Q8_0).

Darkknight535 OpenCrystal 15B L3 v3 – a 15‑billion‑parameter Llama‑3 instruct model

Darkknight535 OpenCrystal 15B L3 v3 is a 15‑billion‑parameter Llama‑3 model fine‑tuned for instruction following. It supports a 8192‑token context window and is available in multiple GGUF quantizations. The model is optimized for logical, coherent responses with reduced hallucinations.

Good at

  • Instruction following
  • Logical reasoning
  • Summarization

Limits

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

Best for

  • Chatbots with 8‑k context
  • Role‑play simulations
  • Content summarization

Who it’s for. Developers building instruction‑driven chat applications or content generators that need a large, coherent language model. The model is suitable for users with access to GPU memory sufficient for the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.7 GB 8.4 GB
Too big Get file →
IQ3_XS6.4 GB 9.0 GB
Too big Get file →
Q3_K_S6.7 GB 9.3 GB
Too big Get file →
IQ3_S6.7 GB 9.3 GB
Too big Get file →
IQ3_M6.9 GB 9.6 GB
Too big Get file →
Q3_K7.4 GB 10.0 GB
Too big Get file →
Q3_K_M7.4 GB 10.0 GB
Too big Get file →
Q3_K_L8.0 GB 10.6 GB
Too big Get file →
IQ4_XS8.3 GB 10.9 GB
Too big Get file →
Q4_08.6 GB 11.2 GB
Too big Get file →
Q4_K_S8.6 GB 11.3 GB
Too big Get file →
IQ4_NL8.7 GB 11.3 GB
Too big Get file →
Q4_K9.1 GB 11.8 GB
Too big Get file →
Q4_K_M9.1 GB 11.8 GB
Too big Get file →
Q4_19.5 GB 12.1 GB
Too big Get file →
Q5_010.4 GB 13.0 GB
Too big Get file →
Q5_K_S10.4 GB 13.0 GB
Too big Get file →
Q5_K10.7 GB 13.3 GB
Too big Get file →
Q5_K_M10.7 GB 13.3 GB
Too big Get file →
Q5_111.3 GB 14.0 GB
Too big Get file →
Q6_K12.3 GB 15.0 GB
Too big Get file →
Q8_016.0 GB 18.6 GB
Too big Get file →

For 8‑GB VRAM, use Q2_K (5.75 GB file, 8.4 GB memory) or IQ3_XS (6.37 GB file, 9 GB memory). For 12‑GB VRAM, Q4_0 (8.59 GB file, 11.2 GB memory) or Q4_K (9.11 GB file, 11.8 GB memory) are good choices. Higher quants like Q6_K or Q8_0 require 15‑GB+ VRAM.

What GPU do you need for Darkknight535 OpenCrystal 15B L3 v3?

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 Q4_K (9.1 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (12.3 GB file, about 15.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (16.0 GB file, about 18.6 GB in use).

Which Darkknight535 OpenCrystal 15B L3 v3 quant should you choose?

Q4_K_M is the usual starting point for Darkknight535 OpenCrystal 15B L3 v3: it balances file size and quality well. Here it is a 9.1 GB file.

The Q8_0 file is 16.0 GB, about 1.8 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 5.7 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
Parameters15B
Layers64
Trained context8,192 tokens
KV cache (fp16)256 KB per token

Source

Quantized byRichardErkhov
Downloads (HF)713
Last updated2024-09-18

Frequently asked questions about Darkknight535 OpenCrystal 15B L3 v3

How much VRAM does Darkknight535 OpenCrystal 15B L3 v3 need?

About 11.8 GB at Q4_K_M with an 8K context window. That is the 9.1 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 Darkknight535 OpenCrystal 15B L3 v3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Darkknight535 OpenCrystal 15B L3 v3 GGUF?

It depends on the quant: Q2_K is 5.7 GB, IQ3_XS is 6.4 GB, Q3_K_S is 6.7 GB, IQ3_S is 6.7 GB, IQ3_M is 6.9 GB, Q3_K is 7.4 GB and 16 more.

What context length does Darkknight535 OpenCrystal 15B L3 v3 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.1 GB at 8K and 2.1 GB at 8K.

Where can I download Darkknight535 OpenCrystal 15B L3 v3 GGUF?

The files are on Hugging Face in the RichardErkhov/Darkknight535_-_OpenCrystal-15B-L3-v3-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 this model on 8 GB VRAM?

Yes, with Q2_K or IQ3_XS quantizations the estimated memory is 8.4–9 GB at 8k context.

Does this model support image input?

No, the model has no vision capabilities.

What context length does it support?

It supports a 8192‑token context window.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Darkknight models

All Darkknight →

Other medium models

All medium models →