QW

Qwen3 4B toolcalling gguf codex

QwenGGUF by ManojbUpdated 2025-09-21
Download on Hugging Face
Parameters4B
Context256K
Layers36
Architectureqwen3
Smallest quant4.3 GB
Quick answer

Qwen3 4B toolcalling gguf codex needs about 6.0 GB of memory at its main file (a 4.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Qwen3 4B toolcalling gguf codex – 4B parameters, 262K context, tool‑calling fine‑tuned

Qwen3 4B toolcalling gguf codex is a 4.0B‑parameter causal language model fine‑tuned on 60K function‑calling examples. It supports a 262,144‑token context and is optimized for local inference in GGUF format. The model is released under the MIT license.

Good at

  • Tool calling
  • Coding assistance
  • Local inference

Limits

  • No vision support
  • Requires 6GB+ VRAM for full precision
  • No thinking mode

Best for

  • Local coding assistants
  • Function‑calling prototypes
  • Privacy‑sensitive AI agents

Who it’s for. Developers who need a lightweight, local tool‑calling model for coding or agentic tasks. The model runs on modern GPUs with 6GB+ VRAM and 8GB+ system RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—4.3 GB 6.0 GB
Fits Get file →

The provided GGUF file is 4.28 GB and requires about 6 GB of memory at 8K context. For 8 GB VRAM, use the default FP16 quantization. If VRAM is limited to 4 GB, consider a lower‑precision quant such as Q4_K_M, which reduces the file size and memory usage.

What GPU do you need for Qwen3 4B toolcalling gguf codex?

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 the main file (4.3 GB file, about 6.0 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters4B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized byManojb
FamilyQwen
Licensemit
Downloads (HF)4,005
Last updated2025-09-21

Frequently asked questions about Qwen3 4B toolcalling gguf codex

How much VRAM does Qwen3 4B toolcalling gguf codex need?

About 6.0 GB at its main file with an 8K context window. That is the 4.3 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 Qwen3 4B toolcalling gguf codex on an 8 GB GPU?

Yes, with the smaller files: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3 4B toolcalling gguf codex GGUF?

It depends on the quant: file is 4.3 GB.

What context length does Qwen3 4B toolcalling gguf codex 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 Qwen3 4B toolcalling gguf codex GGUF?

The files are on Hugging Face in the Manojb/Qwen3-4B-toolcalling-gguf-codex repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Qwen3 4B toolcalling gguf codex 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 Qwen3 4B toolcalling on 8 GB VRAM?

Yes, the model uses about 6 GB of VRAM at 8K context. It will run comfortably on 8 GB VRAM with FP16 quantization.

Does this model support vision tasks?

No, the model only supports text and tool‑calling capabilities.

What license applies to this model?

The model is released under the MIT license, allowing free use for personal and commercial projects.

Other GGUFs of Qwen3-4B-Instruct-2507

Similar models

Browse all →

More from Manojb

All by Manojb →

More Qwen models

All Qwen →

Other small models

All small models →