FR

FrogNano 4B 2609

FrognanoGGUF by SandLogicTechnologiesUpdated 2026-10-16
Download on Hugging Face
Parameters4.33B
Context256K
Layers33
Architectureqwen35
Smallest quant2.2 GB
Quick answer

FrogNano 4B 2609 needs about 4.2 GB of memory at IQ4_XS (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 2.2 GB (IQ3_M) to 3.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

Compact 4B coding agent for repository-level software engineering

FrogNano 4B 2609 is a text‑only model derived from Qwen3.5‑4B, post‑trained for software‑engineering tasks. It supports long context up to 131K tokens and can generate structured tool calls for repository navigation, debugging, and patch generation.

Good at

  • Repository‑level coding tasks
  • Long‑context reasoning
  • Tool‑based code editing

Limits

  • No vision or audio support
  • Requires Leaf harness for tool execution
  • License is Apache‑2.0

Best for

  • Automated bug fixing
  • Codebase navigation
  • Iterative patch generation

Who it’s for. Developers and teams needing a lightweight local agent for repository‑level coding workflows. The model is ideal for environments where local inference and privacy are priorities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M2.2 GB 3.8 GB
Fits Get file →
IQ4_XS2.6 GB 4.2 GB
Fits Get file →
IQ4_NL2.7 GB 4.3 GB
Fits Get file →
Q6_K3.6 GB 5.2 GB
Fits Get file →

For 8 GB VRAM, IQ3_M (2.22 GB) or IQ4_XS (2.59 GB) are suitable, using about 3.8 GB or 4.2 GB of VRAM at 8 k context. If more precision is needed and 12 GB VRAM is available, IQ4_NL (2.69 GB) or Q6_K (3.56 GB) can be used, estimating 4.3 GB or 5.2 GB VRAM usage.

What GPU do you need for FrogNano 4B 2609?

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 (2.2 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 5.2 GB in use).

Which FrogNano 4B 2609 quant should you choose?

IQ4_XS (2.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is IQ3_M at 2.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters4.33B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

FamilyFrognano
Licenseapache-2.0
Downloads (HF)740
Last updated2026-10-16

Frequently asked questions about FrogNano 4B 2609

How much VRAM does FrogNano 4B 2609 need?

About 4.2 GB at IQ4_XS with an 8K context window. That is the 2.6 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 FrogNano 4B 2609 on an 8 GB GPU?

Yes, with Q6_K: the 3.6 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of FrogNano 4B 2609 GGUF?

It depends on the quant: IQ3_M is 2.2 GB, IQ4_XS is 2.6 GB, IQ4_NL is 2.7 GB, Q6_K is 3.6 GB.

What context length does FrogNano 4B 2609 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 4.4 GB at 32K.

Where can I download FrogNano 4B 2609 GGUF?

The files are on Hugging Face in the SandLogicTechnologies/FrogNano-4B-2609-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 FrogNano 4B 2609 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 FrogNano on 8 GB VRAM?

Yes, the IQ3_M and IQ4_XS quantizations fit within 8 GB VRAM, using approximately 3.8 GB and 4.2 GB respectively at 8 k context.

Does FrogNano support image input?

No, FrogNano is text‑only; image and video modalities are not supported.

What license applies to FrogNano?

The model is released under the Apache‑2.0 license.

Other GGUFs of FrogNano-4B-2609

Similar models

Browse all →

More from SandLogicTechnologies

All by SandLogicTechnologies →

More Frognano models

All Frognano →

Other small models

All small models →