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 23 quants, from 7.4 GB (IQ1_S) to 20.8 GB (Q6_K).
KwaiCoder 23B A4B v1 – 23.3B parameter code completion model
KwaiCoder 23B A4B v1 is a 23.3B parameter llama architecture model focused on coding tasks. It is a mixture of experts with 4 active parameters. The model was trained on 4096 context tokens and released under the MIT license.
Good at
- Code completion
- Code insertion
- Large codebase understanding
Limits
- No vision support
- Requires 8k context for memory estimates
- Limited to coding abilities
Best for
- Developers needing code suggestions
- Automated code review tools
- Educational coding assistants
Who it’s for. This model is ideal for developers, educators, and researchers who need a powerful, open‑source code completion tool. It is suitable for integration into IDEs, code editors, or custom tooling where coding assistance is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 7.4 GB | 9.3 GB | Too big | Get file → | |
| IQ1_M | 7.8 GB | 9.6 GB | Too big | Get file → | |
| IQ2_XXS | 8.4 GB | 10.2 GB | Too big | Get file → | |
| IQ2_XS | 8.9 GB | 10.7 GB | Too big | Get file → | |
| IQ2_S | 8.9 GB | 10.8 GB | Too big | Get file → | |
| IQ2_M | 9.4 GB | 11.2 GB | Too big | Get file → | |
| Q2_K | 9.5 GB | 11.3 GB | Too big | Get file → | |
| Q2_K_S | 9.5 GB | 11.3 GB | Too big | Get file → | |
| IQ3_XXS | 10.2 GB | 12.1 GB | Too big | Get file → | |
| IQ3_XS | 10.5 GB | 12.3 GB | Too big | Get file → | |
| IQ3_S | 11.0 GB | 12.9 GB | Too big | Get file → | |
| Q3_K_S | 11.0 GB | 12.9 GB | Too big | Get file → | |
| IQ3_M | 11.2 GB | 13.0 GB | Too big | Get file → | |
| Q3_K_M | 12.0 GB | 13.9 GB | Too big | Get file → | |
| Q3_K_L | 12.5 GB | 14.4 GB | Too big | Get file → | |
| IQ4_XS | 12.6 GB | 14.5 GB | Too big | Get file → | |
| Q4_0 | 13.2 GB | 15.0 GB | Too big | Get file → | |
| Q4_K_S | 14.1 GB | 15.9 GB | Too big | Get file → | |
| Q4_1 | 14.6 GB | 16.4 GB | Too big | Get file → | |
| Q4_K_M | 15.4 GB | 17.3 GB | Too big | Get file → | |
| Q5_K_S | 16.5 GB | 18.3 GB | Too big | Get file → | |
| Q5_K_M | 17.6 GB | 19.5 GB | Too big | Get file → | |
| Q6_K | 20.8 GB | 22.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 7.44 GB, estimated 10.6 GB memory). For 12 GB VRAM, IQ1_M (7.79 GB, 11 GB memory) or IQ2_XXS (8.38 GB, 11.6 GB memory). For 18 GB VRAM, Q4_K_M (15.43 GB, 18.6 GB memory) is recommended. Memory estimates are approximate.
What GPU do you need for 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: the best quant that fits is IQ2_XS (8.9 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (12.6 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (20.8 GB file, about 24.0 GB in use).
Which KwaiCoder 23B A4B v1 quant should you choose?
Q4_K_M is the usual starting point for KwaiCoder 23B A4B v1: it balances file size and quality well. Here it is a 15.4 GB file.
If memory is tight, the smallest file is IQ1_S at 7.4 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
Source
Frequently asked questions about KwaiCoder 23B A4B v1
How much VRAM does 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 KwaiCoder 23B A4B v1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of KwaiCoder 23B A4B v1 GGUF?
It depends on the quant: IQ1_S is 7.4 GB, IQ1_M is 7.8 GB, IQ2_XXS is 8.4 GB, IQ2_XS is 8.9 GB, IQ2_S is 8.9 GB, IQ2_M is 9.4 GB and 17 more.
What context length does 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 KwaiCoder 23B A4B v1 GGUF?
The files are on Hugging Face in the mradermacher/KwaiCoder-23B-A4B-v1-i1-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 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.
Can I run KwaiCoder 23B A4B v1 on 8 GB VRAM?
Yes, the IQ1_S quant requires about 10.6 GB of VRAM at 8k context, which is close to 8 GB but may need off‑load or lower context.
Does this model support image inputs?
No, the model has no vision capabilities.
What license does it use?
The model is released under the MIT license.