KI

Agents A1 4B kimi Preview

KimiGGUF by hotdogsUpdated 2026-07-30
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant2.6 GB
Quick answer

Agents A1 4B kimi Preview needs about 6.1 GB of memory at Q8_0 (a 4.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 2.6 GB (IQ4_NL) to 8.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

4B coding agent model with vision and tool‑calling

Agents A1 4B kimi Preview is a 4.21B parameter model fine‑tuned on Kimi K3 coding and debugging traces. It supports reasoning, tool use, and vision via mmproj. The model is released under agpl‑3.0.

Good at

  • Coding agent tasks
  • Step‑by‑step reasoning
  • Tool‑calling

Limits

  • No vision support without mmproj
  • Large context requires high VRAM
  • License is agpl‑3.0

Best for

  • Debugging code
  • Building projects
  • Multi‑step tool workflows

Who it’s for. Developers needing a coding assistant that can reason, call tools, and process images. Suitable for projects that require a lightweight 4B model with vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_NL2.6 GB 4.2 GB
Fits Get file →
Q8_04.5 GB 6.1 GB
Fits Get file →
—8.4 GB 10.0 GB
Too big Get file →

For 8 GB VRAM, use IQ4_NL (2.61 GB file, 4.2 GB memory at 8K context). For 12 GB VRAM, Q8_0 (4.48 GB file, 6.1 GB memory at 8K context). Larger models need more VRAM.

What GPU do you need for Agents A1 4B kimi Preview?

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: the best quant that fits is IQ4_NL (2.6 GB file, about 4.2 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (8.4 GB file, about 10.0 GB in use).

Which Agents A1 4B kimi Preview quant should you choose?

Q8_0 (4.5 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is IQ4_NL at 2.6 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters4.21B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byhotdogs
FamilyKimi
Licenseagpl-3.0
Downloads (HF)603
Last updated2026-07-30

Frequently asked questions about Agents A1 4B kimi Preview

How much VRAM does Agents A1 4B kimi Preview need?

About 6.1 GB at Q8_0 with an 8K context window. That is the 4.5 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 Agents A1 4B kimi Preview on an 8 GB GPU?

Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Agents A1 4B kimi Preview GGUF?

It depends on the quant: IQ4_NL is 2.6 GB, Q8_0 is 4.5 GB, file is 8.4 GB.

What context length does Agents A1 4B kimi Preview support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Agents A1 4B kimi Preview GGUF?

The files are on Hugging Face in the hotdogs/Agents-A1-4B-kimi-Preview-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 Agents A1 4B kimi Preview use?

Hugging Face lists the license as agpl-3.0. 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?

Yes, the IQ4_NL quantization fits 8 GB VRAM and uses 4.2 GB memory at 8K context.

Does it support vision?

Vision is available via the mmproj projector included in the GGUF release.

What license does it use?

The model is released under the agpl‑3.0 license.

Similar models

Browse all →

More from hotdogs

All by hotdogs →

More Kimi models

All Kimi →

Other small models

All small models →