QW

Qwen2-72B-Orpo-v0.1

QwenGGUF by mradermacherUpdated 2024-07-22
Download on Hugging Face
Parameters72.7B
Context32K
Layers80
Architectureqwen2
Smallest quant29.8 GB
Quick answer

Qwen2-72B-Orpo-v0.1 needs about 50.6 GB of memory at Q4_K_M (a 47.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 10 quants, from 29.8 GB (Q2_K) to 47.4 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Qwen2-72B-Orpo-v0.1 – a 72.7B parameter instruction fine‑tuned model

Qwen2-72B-Orpo-v0.1 is a 72.7B parameter model fine‑tuned on 1.5k rows of orpo-dpo-mix-40k. It supports generalist text generation, agentic tasks, roleplaying, reasoning, multi‑turn conversation, and long‑context coherence. The model is available in GGUF format.

Good at

  • Long‑context text generation
  • Agentic and multi‑turn dialogue
  • Reasoning and roleplaying

Limits

  • No vision support
  • Large VRAM requirement for higher quants
  • License type is other

Best for

  • Chatbots needing long context
  • Research on instruction following
  • Developers building agentic applications

Who it’s for. Developers and researchers who need a large instruction‑tuned model for complex text generation tasks. The model is suitable for environments that can accommodate its memory footprint and do not require vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K29.8 GB 33.0 GB
Too big Get file →
IQ3_XS32.8 GB 36.0 GB
Too big Get file →
IQ3_S34.5 GB 37.7 GB
Too big Get file →
Q3_K_S34.5 GB 37.7 GB
Too big Get file →
IQ3_M35.5 GB 38.7 GB
Too big Get file →
Q3_K_M37.7 GB 40.9 GB
Too big Get file →
Q3_K_L39.5 GB 42.7 GB
Too big Get file →
IQ4_XS40.2 GB 43.3 GB
Too big Get file →
Q4_K_S43.9 GB 47.1 GB
Too big Get file →
Q4_K_M47.4 GB 50.6 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 29.81 GB, estimated 33 GB memory). For 12 GB VRAM, Q3_K_S (34.48 GB, 37.7 GB memory) is a good balance. For 16 GB VRAM, Q4_K_S (43.88 GB, 47.1 GB memory) offers higher quality while staying within limits.

What GPU do you need for Qwen2-72B-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: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q4_K_S (43.9 GB file, about 47.1 GB in use).

Which Qwen2-72B-Orpo-v0.1 quant should you choose?

Q4_K_M is the usual starting point for Qwen2-72B-Orpo-v0.1: it balances file size and quality well. Here it is a 47.4 GB file.

If memory is tight, the smallest file is Q2_K at 29.8 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

Architectureqwen2
Parameters72.7B
Layers80
Trained context32,768 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseother
Downloads (HF)567
Last updated2024-07-22

Frequently asked questions about Qwen2-72B-Orpo-v0.1

How much VRAM does Qwen2-72B-Orpo-v0.1 need?

About 50.6 GB at Q4_K_M with an 8K context window. That is the 47.4 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 Qwen2-72B-Orpo-v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 33.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen2-72B-Orpo-v0.1 GGUF?

It depends on the quant: Q2_K is 29.8 GB, IQ3_XS is 32.8 GB, IQ3_S is 34.5 GB, Q3_K_S is 34.5 GB, IQ3_M is 35.5 GB, Q3_K_M is 37.7 GB and 4 more.

What context length does Qwen2-72B-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 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Qwen2-72B-Orpo-v0.1 GGUF?

The files are on Hugging Face in the mradermacher/Qwen2-72B-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 Qwen2-72B-Orpo-v0.1 use?

Hugging Face lists the license as other. 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 Qwen2-72B-Orpo-v0.1 on 8 GB VRAM?

The smallest quant, Q2_K, requires about 33 GB memory at 8k context, so 8 GB VRAM is insufficient.

Which quant provides the best quality for a 12 GB VRAM setup?

Q3_K_S offers a balance of quality and memory usage, needing about 37.7 GB at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of Qwen2-72B-Orpo-v0.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other large models

All large models →