FR

FrogNano 4B 2609

FrognanoGGUF by richardyoungUpdated 2026-10-20
Download on Hugging Face
Parameters4.33B
Context256K
Layers33
Architectureqwen35
Smallest quant0.0 GB
Quick answer

FrogNano 4B 2609 needs about 4.4 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 7 quants, from 0.0 GB to 4.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

FrogNano 4B 2609 – a 4.33B parameter coding agent

FrogNano 4B 2609 is a 4.33B parameter model derived from Qwen3.5-4B. It is post‑trained with reinforcement learning on synthetic software‑engineering tasks and supports up to 262,144 token context. The model is licensed under MIT and includes a vision projector.

Good at

  • Repository‑level code editing
  • Multi‑turn coding with tool calls
  • Long‑context reasoning

Limits

  • No vision training beyond inherited projector
  • Sensitive to Leaf harness quality
  • No non‑English training data

Best for

  • Local coding agents
  • Code review assistants
  • Research on RL‑trained agents

Who it’s for. Developers and researchers who need a lightweight, local coding assistant that can navigate and edit codebases. The model is suitable for environments where local inference and tool integration are required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 GB
Fits Get file →
IQ3_M2.2 GB 3.8 GB
Fits Get file →
IQ4_XS2.6 GB 4.2 GB
Fits Get file →
Q4_K_M2.8 GB 4.4 GB
Fits Get file →
Q5_K_M3.2 GB 4.8 GB
Fits Get file →
Q6_K3.6 GB 5.2 GB
Fits Get file →
Q8_04.6 GB 6.2 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (2.78 GB file, ~4.4 GB memory). For 6 GB VRAM, use IQ4_XS (2.58 GB file, ~4.2 GB memory). For 4 GB VRAM, use IQ3_M (2.22 GB file, ~3.8 GB memory). Estimates are approximate.

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).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.6 GB file, about 6.2 GB in use).

Which FrogNano 4B 2609 quant should you choose?

Q4_K_M is the usual starting point for FrogNano 4B 2609: it balances file size and quality well. Here it is a 2.8 GB file.

The Q8_0 file is 4.6 GB, about 1.7 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

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

Source

Quantized byrichardyoung
FamilyFrognano
Licensemit
Downloads (HF)778
Last updated2026-10-20

Frequently asked questions about FrogNano 4B 2609

How much VRAM does FrogNano 4B 2609 need?

About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.8 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 Q8_0: the 4.6 GB file needs about 6.2 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: file is 0.0 GB, IQ3_M is 2.2 GB, IQ4_XS is 2.6 GB, Q4_K_M is 2.8 GB, Q5_K_M is 3.2 GB, Q6_K is 3.6 GB and 1 more.

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 richardyoung/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 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 FrogNano 4B 2609 on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 4.4 GB of VRAM at 8 k context, which fits within 8 GB.

Does FrogNano support vision tasks?

It includes a vision projector inherited from Qwen3.5-4B, but it was not post‑trained for vision.

What license does FrogNano have?

The model is released under the MIT license.

Other GGUFs of FrogNano-4B-2609

Similar models

Browse all →

More from richardyoung

All by richardyoung →

More Frognano models

All Frognano →

Other small models

All small models →