QW

calme 2.1 qwen2 72b

QwenGGUF by MaziyarPanahiUpdated 2024-08-02
Download on Hugging Face
Parameters72.7B
Context32K
Layers80
Architectureqwen2
Smallest quant22.7 GB
Quick answer

calme 2.1 qwen2 72b 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 15 quants, from 22.7 GB (IQ1_S) to 77.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Fine‑tuned Qwen2‑72B with 32k context

calme 2.1 qwen2 72b is a 72.7 billion‑parameter model based on Qwen2. It supports a 32768‑token context window and is available in multiple GGUF quantizations. The model is fine‑tuned to improve performance across benchmarks.

Good at

  • Large context handling
  • High‑parameter inference
  • Fine‑tuned instruction following

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is other

Best for

  • Long‑form content generation
  • Complex reasoning tasks
  • Research prototyping

Who it’s for. Developers and researchers needing a large‑scale language model with extended context. The model is suitable for environments that can accommodate its memory requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S22.7 GB (8 parts) 25.9 GB
Too big Get file →
IQ1_M23.7 GB (8 parts) 26.9 GB
Too big Get file →
IQ2_XS27.1 GB (8 parts) 30.2 GB
Too big Get file →
Q2_K29.8 GB (8 parts) 33.0 GB
Too big Get file →
IQ3_XS32.8 GB (8 parts) 36.0 GB
Too big Get file →
Q3_K_S34.5 GB (8 parts) 37.7 GB
Too big Get file →
Q3_K_M37.7 GB (8 parts) 40.9 GB
Too big Get file →
Q3_K_L39.5 GB (8 parts) 42.7 GB
Too big Get file →
IQ4_XS39.7 GB (8 parts) 42.9 GB
Too big Get file →
Q4_K_S43.9 GB (8 parts) 47.1 GB
Too big Get file →
Q4_K_M47.4 GB (8 parts) 50.6 GB
Too big Get file →
Q5_K_S51.4 GB (8 parts) 54.6 GB
Too big Get file →
Q5_K_M54.4 GB (8 parts) 57.6 GB
Too big Get file →
Q6_K64.3 GB (8 parts) 67.5 GB
Too big Get file →
Q8_077.3 GB (8 parts) 80.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (22.69 GB file, 25.9 GB memory at 8k). For 16 GB VRAM, IQ2_XS (27.05 GB file, 30.2 GB memory). For 32 GB VRAM, Q4_K_M (47.41 GB file, 50.6 GB memory). Estimates are approximate.

What GPU do you need for calme 2.1 qwen2 72b?

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_XS (27.1 GB file, about 30.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_S (43.9 GB file, about 47.1 GB in use).

Which calme 2.1 qwen2 72b quant should you choose?

Q4_K_M is the usual starting point for calme 2.1 qwen2 72b: it balances file size and quality well. Here it is a 47.4 GB file.

The Q8_0 file is 77.3 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_S at 22.7 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

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

Source

Quantized byMaziyarPanahi
FamilyQwen
Licenseother
Downloads (HF)2,546
Last updated2024-08-02

Frequently asked questions about calme 2.1 qwen2 72b

How much VRAM does calme 2.1 qwen2 72b 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 calme 2.1 qwen2 72b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 25.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of calme 2.1 qwen2 72b GGUF?

It depends on the quant: IQ1_S is 22.7 GB, IQ1_M is 23.7 GB, IQ2_XS is 27.1 GB, Q2_K is 29.8 GB, IQ3_XS is 32.8 GB, Q3_K_S is 34.5 GB and 9 more.

What context length does calme 2.1 qwen2 72b 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 calme 2.1 qwen2 72b GGUF?

The files are on Hugging Face in the MaziyarPanahi/calme-2.1-qwen2-72b-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 calme 2.1 qwen2 72b 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 this model on 8 GB VRAM?

Use the IQ1_S quantization; it requires about 25.9 GB of VRAM at 8k context, so 8 GB is insufficient.

Does this model support vision tasks?

No, the model has no vision capabilities.

What prompt template does it use?

It uses the ChatML prompt template.

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Qwen models

All Qwen →

Other large models

All large models →