CA

CalmeRys 78B Orpo v0.1

CalmerysGGUF by bartowskiUpdated 2024-09-30
Download on Hugging Face
Parameters78B
Context32K
Layers86
Architectureqwen2
Smallest quant25.4 GB
Quick answer

CalmeRys 78B Orpo v0.1 needs about 54.1 GB of memory at Q4_K_M (a 50.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 18 quants, from 25.4 GB (IQ1_M) to 82.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 11.5 GB.

CalmeRys 78B Orpo v0.1 – 78B parameter Qwen2 model

CalmeRys 78B Orpo v0.1 is a 78B parameter Qwen2 model fine‑tuned on 1.5k rows of the mlabonne/orpo-dpo-mix-40k dataset. It supports generalist text generation, agentic capabilities, roleplaying, reasoning, multi‑turn conversation, and long‑context coherence.

Good at

  • Generalist text generation
  • Agentic and roleplaying tasks
  • Long‑context coherence

Limits

  • No vision support
  • Large VRAM requirement for full precision
  • MIT license limits commercial use without attribution

Best for

  • Chatbots requiring deep reasoning
  • Creative writing assistants
  • Simulated agent interactions

Who it’s for. Developers and researchers building advanced conversational agents or large‑scale text generation pipelines. The model is suitable for users with high‑end GPUs or sufficient RAM to host the quantized weights.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M25.4 GB 28.8 GB
Too big Get file →
IQ2_XXS27.3 GB 30.7 GB
Too big Get file →
IQ2_XS29.0 GB 32.4 GB
Too big Get file →
IQ2_M31.4 GB 34.8 GB
Too big Get file →
Q2_K31.8 GB 35.2 GB
Too big Get file →
Q2_K_L33.1 GB 36.4 GB
Too big Get file →
IQ3_XXS34.0 GB 37.4 GB
Too big Get file →
Q3_K_S36.8 GB 40.2 GB
Too big Get file →
IQ3_M37.9 GB 41.3 GB
Too big Get file →
Q3_K_M40.3 GB 43.7 GB
Too big Get file →
Q3_K_L42.3 GB 45.7 GB
Too big Get file →
IQ4_XS42.6 GB 45.9 GB
Too big Get file →
Q3_K_XL43.4 GB 46.8 GB
Too big Get file →
Q4_044.3 GB 47.7 GB
Too big Get file →
Q4_K_M50.7 GB (2 parts) 54.1 GB
Too big Get file →
Q5_K_M58.3 GB (2 parts) 61.7 GB
Too big Get file →
Q6_K69.0 GB (2 parts) 72.4 GB
Too big Get file →
Q8_082.9 GB (3 parts) 86.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 44.34 GB, memory 47.7 GB). For 16 GB VRAM, Q4_K_M (file size 50.7 GB, memory 54.1 GB) or Q5_K_M (58.31 GB, 61.7 GB). For 24 GB VRAM, Q6_K (69.01 GB, 72.4 GB) or Q8_0 (82.85 GB, 86.2 GB). Estimates are approximate.

What GPU do you need for CalmeRys 78B Orpo v0.1?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ2_XXS (27.3 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_0 (44.3 GB file, about 47.7 GB in use).

Which CalmeRys 78B Orpo v0.1 quant should you choose?

Q4_K_M is the usual starting point for CalmeRys 78B Orpo v0.1: it balances file size and quality well. Here it is a 50.7 GB file.

The Q8_0 file is 82.9 GB, about 1.6 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 IQ1_M at 25.4 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

Architectureqwen2
Parameters78B
Layers86
Trained context32,768 tokens
KV cache (fp16)344 KB per token

Source

Quantized bybartowski
FamilyCalmerys
Licensemit
Downloads (HF)1,151
Last updated2024-09-30

Frequently asked questions about CalmeRys 78B Orpo v0.1

How much VRAM does CalmeRys 78B Orpo v0.1 need?

About 54.1 GB at Q4_K_M with an 8K context window. That is the 50.7 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 CalmeRys 78B Orpo v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of CalmeRys 78B Orpo v0.1 GGUF?

It depends on the quant: IQ1_M is 25.4 GB, IQ2_XXS is 27.3 GB, IQ2_XS is 29.0 GB, IQ2_M is 31.4 GB, Q2_K is 31.8 GB, Q2_K_L is 33.1 GB and 12 more.

What context length does CalmeRys 78B Orpo v0.1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.9 GB at 8K and 11.5 GB at 32K.

Where can I download CalmeRys 78B Orpo v0.1 GGUF?

The files are on Hugging Face in the bartowski/CalmeRys-78B-Orpo-v0.1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does CalmeRys 78B Orpo v0.1 use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run CalmeRys 78B Orpo v0.1 on 8 GB VRAM?

Use the Q4_0 quant; it requires about 47.7 GB of VRAM, so 8 GB is insufficient.

Does the model support vision tasks?

No, the model has no vision capability.

What license does the model use?

MIT license; commercial use requires attribution.

Other GGUFs of CalmeRys-78B-Orpo-v0.1

Similar models

Browse all →

More from bartowski

All by bartowski →

More Calmerys models

All Calmerys →

Other large models

All large models →