QW

AesCoder-4B

QwenGGUF by MungertUpdated 2025-11-14
Download on Hugging Face
Parameters4.41B
Context256K
Layers36
Architectureqwen3
Smallest quant0.0 GB
Quick answer

AesCoder-4B needs about 4.7 GB of memory at Q4_K_M (a 3.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 8.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

AesCoder-4B – a 4.41B‑parameter Qwen3 model for coding and reasoning

AesCoder-4B is a Qwen3‑based causal language model with 4.41B parameters. It supports a 262,144‑token context length and is optimized for instruction following, coding, reasoning, and tool usage. The model is released under the Apache‑2.0 license.

Good at

  • Coding and code generation
  • Logical reasoning and problem solving
  • Tool calling and agentic workflows

Limits

  • No vision support
  • Requires non‑thinking mode only
  • Large VRAM needed for higher‑bit quantizations

Best for

  • Local code generation in IDEs
  • Automated bug fixing scripts
  • Tool‑enabled agentic applications

Who it’s for. Developers and researchers who need a compact yet capable model for code‑centric tasks. The model is suitable for local deployment with llama.cpp or other GGUF‑compatible runtimes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.7 GB
Fits Get file →
IQ2_XXS1.6 GB 3.3 GB
Fits Get file →
IQ2_XS1.7 GB 3.4 GB
Fits Get file →
IQ2_S1.8 GB 3.5 GB
Fits Get file →
Q2_K_S1.8 GB 3.5 GB
Fits Get file →
IQ2_M1.8 GB 3.5 GB
Fits Get file →
Q2_K_M1.9 GB 3.6 GB
Fits Get file →
IQ3_XXS2.1 GB 3.8 GB
Fits Get file →
IQ3_XS2.1 GB 3.9 GB
Fits Get file →
Q3_K_S2.3 GB 4.0 GB
Fits Get file →
IQ3_M2.3 GB 4.0 GB
Fits Get file →
Q3_K_M2.4 GB 4.1 GB
Fits Get file →
IQ4_NL2.5 GB 4.2 GB
Fits Get file →
IQ4_XS2.6 GB 4.3 GB
Fits Get file →
Q4_K_S2.7 GB 4.4 GB
Fits Get file →
Q4_12.8 GB 4.5 GB
Fits Get file →
Q4_02.9 GB 4.6 GB
Fits Get file →
Q4_K_M3.0 GB 4.7 GB
Fits Get file →
Q5_03.3 GB 5.0 GB
Fits Get file →
Q5_K_M3.4 GB 5.1 GB
Fits Get file →
Q5_13.6 GB 5.3 GB
Fits Get file →
Q6_K_M3.8 GB 5.5 GB
Fits Get file →
Q8_04.7 GB 6.4 GB
Fits Get file →
F166.7 GB 8.4 GB
Too big Get file →
BF168.8 GB 10.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.99 GB, memory 4.7 GB at 8 k context). If 12 GB VRAM is available, Q5_K_M (3.41 GB, 5.1 GB) offers higher precision. For the lowest memory footprint, IQ2_XXS (1.61 GB, 3.3 GB) is recommended, though it has the lowest accuracy.

What GPU do you need for AesCoder-4B?

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: the best quant that fits is IQ3_M (2.3 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K_M (3.8 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.7 GB file, about 6.4 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.8 GB file, about 10.5 GB in use).

Which AesCoder-4B quant should you choose?

Q4_K_M is the usual starting point for AesCoder-4B: it balances file size and quality well. Here it is a 3.0 GB file.

The Q8_0 file is 4.7 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters4.41B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized byMungert
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,032
Last updated2025-11-14

Frequently asked questions about AesCoder-4B

How much VRAM does AesCoder-4B need?

About 4.7 GB at Q4_K_M with an 8K context window. That is the 3.0 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 AesCoder-4B on an 8 GB GPU?

Yes, with Q8_0: the 4.7 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of AesCoder-4B GGUF?

It depends on the quant: file is 0.0 GB, IQ2_XXS is 1.6 GB, IQ2_XS is 1.7 GB, IQ2_S is 1.8 GB, Q2_K_S is 1.8 GB, IQ2_M is 1.8 GB and 19 more.

What context length does AesCoder-4B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download AesCoder-4B GGUF?

The files are on Hugging Face in the Mungert/AesCoder-4B-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 AesCoder-4B use?

Hugging Face lists the license as apache-2.0. 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 AesCoder-4B on 8 GB VRAM?

Yes, with a Q4_K_M quantization the model uses about 4.7 GB of VRAM at 8 k context. Lower‑bit quantizations reduce VRAM further.

Does AesCoder-4B support vision tasks?

No, the model does not include vision capabilities.

What license applies to AesCoder-4B?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3-4B-Instruct-2507

Similar models

Browse all →

More from Mungert

All by Mungert →

More Qwen models

All Qwen →

Other small models

All small models →