XW

XwinXtended 20B i1

XwinxtendedGGUF by mradermacherUpdated 2024-09-27
Download on Hugging Face
Parameters20B
Context4K
Layers62
Architecturellama
Smallest quant4.4 GB
Quick answer

XwinXtended 20B i1 needs about 22.9 GB of memory at Q4_K_M (a 12.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 4.4 GB (IQ1_S) to 16.4 GB (Q6_K).

20B XwinXtended model with multiple IQ and Q quant options

XwinXtended 20B i1 is a 20B parameter model merged from Xwin-LM-13B-V0.2. It supports a 4096 token context and offers a range of IQ and Q quantizations. The model is available in GGUF format via the Hugging Face repository.

Good at

  • Creative prose generation
  • Long context handling up to 4096 tokens
  • Supports IQ and Q quantizations

Limits

  • No license specified
  • Requires large VRAM for higher quants
  • No vision capabilities

Best for

  • Writing long narratives
  • Chatbot with extended context
  • Fine‑tuning on custom datasets

Who it’s for. Developers who need a 20B LLM with flexible quantization and extended context. Ideal for those who can allocate sufficient GPU memory and require high‑quality text generation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.4 GB 10.1 GB
Too big Get file →
IQ1_M4.8 GB 10.5 GB
Too big Get file →
IQ2_XXS5.4 GB 11.1 GB
Too big Get file →
IQ2_XS5.9 GB 11.6 GB
Too big Get file →
IQ2_S6.4 GB 12.1 GB
Too big Get file →
IQ2_M6.9 GB 12.6 GB
Too big Get file →
Q2_K7.4 GB 13.1 GB
Too big Get file →
IQ3_XXS7.6 GB 13.3 GB
Too big Get file →
IQ3_XS8.2 GB 13.9 GB
Too big Get file →
IQ3_S8.7 GB 14.4 GB
Too big Get file →
Q3_K_S8.7 GB 14.4 GB
Too big Get file →
IQ3_M9.2 GB 14.9 GB
Too big Get file →
Q3_K_M9.7 GB 15.4 GB
Too big Get file →
Q3_K_L10.6 GB 16.3 GB
Too big Get file →
IQ4_XS10.7 GB 16.4 GB
Too big Get file →
Q4_011.3 GB 17.0 GB
Too big Get file →
Q4_K_S11.4 GB 17.1 GB
Too big Get file →
Q4_K_M12.0 GB 17.7 GB
Too big Get file →
Q5_K_S13.8 GB 19.5 GB
Too big Get file →
Q5_K_M14.2 GB 19.9 GB
Too big Get file →
Q6_K16.4 GB 22.1 GB
Too big Get file →

For 16‑GB VRAM, use IQ2_S (file size 6.4 GB, estimated 17.3 GB memory). For 24‑GB VRAM, IQ3_M (9.16 GB, 20.1 GB memory) or Q4_K_M (12.04 GB, 22.9 GB memory) are suitable. Higher quants need more than 32 GB VRAM.

What GPU do you need for XwinXtended 20B i1?

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: the best quant that fits is IQ1_M (4.8 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (12.0 GB file, about 22.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (16.4 GB file, about 27.3 GB in use).

Which XwinXtended 20B i1 quant should you choose?

Q4_K_M is the usual starting point for XwinXtended 20B i1: it balances file size and quality well. Here it is a 12.0 GB file.

If memory is tight, the smallest file is IQ1_S at 4.4 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

Architecturellama
Parameters20B
Layers62
Trained context4,096 tokens
KV cache (fp16)1240 KB per token

Source

Quantized bymradermacher
Downloads (HF)1,500
Last updated2024-09-27

Frequently asked questions about XwinXtended 20B i1

How much VRAM does XwinXtended 20B i1 need?

About 22.9 GB at Q4_K_M with an 8K context window. That is the 12.0 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 XwinXtended 20B i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of XwinXtended 20B i1 GGUF?

It depends on the quant: IQ1_S is 4.4 GB, IQ1_M is 4.8 GB, IQ2_XXS is 5.4 GB, IQ2_XS is 5.9 GB, IQ2_S is 6.4 GB, IQ2_M is 6.9 GB and 15 more.

What context length does XwinXtended 20B i1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 10.4 GB at 8K and 5.2 GB at 4K.

Where can I download XwinXtended 20B i1 GGUF?

The files are on Hugging Face in the mradermacher/XwinXtended-20B-i1-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 IQ1_S on 16 GB VRAM?

IQ1_S requires about 15.3 GB memory at 8k context, so 16 GB VRAM is borderline but may work with lower batch sizes.

What is the context length?

The model supports a maximum context length of 4096 tokens.

Does it support vision?

No, the model has no vision capabilities.

Other GGUFs of XwinXtended-20B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Xwinxtended models

All Xwinxtended →

Other medium models

All medium models →