KW

Kwaipilot.KwaiCoder 23B A4B v1

KwaicoderGGUF by DevQuasarUpdated 2025-07-25
Download on Hugging Face
Parameters23.3B
Context4K
Layers20
Architecturellama
Smallest quant9.5 GB
Quick answer

Kwaipilot.KwaiCoder 23B A4B v1 needs about 18.6 GB of memory at Q4_K_M (a 15.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 9.5 GB (Q2_K) to 46.5 GB (F16).

Kwaipilot.KwaiCoder 23B A4B v1 is a 23.3B-parameter Kwaicoder model in GGUF format, quantized by DevQuasar. Its trained context length is 4K tokens. The repository has 11 quant files, from 9.5 GB (Q2_K) to 46.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K9.5 GB 11.3 GB
Too big Get file →
Q3_K_S11.0 GB 12.9 GB
Too big Get file →
Q3_K_M12.0 GB 13.9 GB
Too big Get file →
Q3_K_L12.5 GB 14.4 GB
Too big Get file →
Q4_K_S14.1 GB 15.9 GB
Too big Get file →
Q4_K_M15.4 GB 17.3 GB
Too big Get file →
Q5_K_S16.5 GB 18.3 GB
Too big Get file →
Q5_K_M17.6 GB 19.5 GB
Too big Get file →
Q6_K20.8 GB 22.7 GB
Too big Get file →
Q8_024.7 GB 26.6 GB
Too big Get file →
F1646.5 GB (2 parts) 48.4 GB
Too big Get file →

What GPU do you need for Kwaipilot.KwaiCoder 23B A4B v1?

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 Q3_K_L (12.5 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (20.8 GB file, about 24.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (24.7 GB file, about 27.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (24.7 GB file, about 27.9 GB in use).

Which Kwaipilot.KwaiCoder 23B A4B v1 quant should you choose?

Q4_K_M is the usual starting point for Kwaipilot.KwaiCoder 23B A4B v1: it balances file size and quality well. Here it is a 15.4 GB file.

The Q8_0 file is 24.7 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 Q2_K at 9.5 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
Parameters23.3B (approximate, mixture of experts)
Active parameters4B
Layers20
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byDevQuasar
FamilyKwaicoder
Licensemit
Downloads (HF)216
Last updated2025-07-25

Frequently asked questions about Kwaipilot.KwaiCoder 23B A4B v1

How much VRAM does Kwaipilot.KwaiCoder 23B A4B v1 need?

About 18.6 GB at Q4_K_M with an 8K context window. That is the 15.4 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 Kwaipilot.KwaiCoder 23B A4B v1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kwaipilot.KwaiCoder 23B A4B v1 GGUF?

It depends on the quant: Q2_K is 9.5 GB, Q3_K_S is 11.0 GB, Q3_K_M is 12.0 GB, Q3_K_L is 12.5 GB, Q4_K_S is 14.1 GB, Q4_K_M is 15.4 GB and 5 more.

What context length does Kwaipilot.KwaiCoder 23B A4B v1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download Kwaipilot.KwaiCoder 23B A4B v1 GGUF?

The files are on Hugging Face in the DevQuasar/Kwaipilot.KwaiCoder-23B-A4B-v1-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 Kwaipilot.KwaiCoder 23B A4B v1 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.

Other GGUFs of KwaiCoder-23B-A4B-v1

Similar models

Browse all →

More from DevQuasar

All by DevQuasar →

More Kwaicoder models

All Kwaicoder →

Other medium models

All medium models →