FR

FrogNano 4B 2609

FrognanoGGUF by NANI-NithinUpdated 2026-10-04
Download on Hugging Face
Parameters4.33B
Context256K
Layers33
Architectureqwen35
Smallest quant1.1 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 30 quants, from 1.1 GB (Q1_0) to 8.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

FrogNano 4B 2609 – a compact coding agent for repository-level tasks

FrogNano 4B 2609 is a 4.3 B parameter model based on Qwen3.5-4B. It is post‑trained with reinforcement learning on synthetic software‑engineering tasks and is designed for code navigation, debugging, and patch generation. The model supports a combined context length of about 131 K tokens and includes vision capabilities.

Good at

  • Repository‑level code editing
  • Multi‑file patch generation
  • Long‑context reasoning

Limits

  • Requires 8 K context for memory estimates
  • No native vision support in GGUF runtime
  • License is MIT – no commercial restrictions

Best for

  • Automated code review pipelines
  • Interactive coding assistants
  • Debugging large codebases

Who it’s for. Developers and teams needing a lightweight, repository‑aware LLM for coding tasks. The model is suitable for integration with the Leaf harness to generate structured tool calls for file operations and test execution.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q1_01.1 GB 2.7 GB
Fits Get file →
IQ1_S1.4 GB 3.0 GB
Fits Get file →
IQ1_M1.5 GB 3.1 GB
Fits Get file →
IQ2_XXS1.6 GB 3.2 GB
Fits Get file →
Q2_01.6 GB 3.2 GB
Fits Get file →
IQ2_XS1.7 GB 3.3 GB
Fits Get file →
IQ2_S1.7 GB 3.3 GB
Fits Get file →
IQ2_M1.8 GB 3.4 GB
Fits Get file →
Q2_K_S1.9 GB 3.5 GB
Fits Get file →
IQ3_XXS2.0 GB 3.6 GB
Fits Get file →
Q2_K2.0 GB 3.6 GB
Fits Get file →
Q3_K_S2.1 GB 3.7 GB
Fits Get file →
IQ3_XS2.1 GB 3.8 GB
Fits Get file →
IQ3_S2.2 GB 3.8 GB
Fits Get file →
IQ3_M2.2 GB 3.8 GB
Fits Get file →
Q3_K_M2.3 GB 3.9 GB
Fits Get file →
Q3_K_L2.5 GB 4.1 GB
Fits Get file →
IQ4_XS2.6 GB 4.2 GB
Fits Get file →
Q4_02.6 GB 4.2 GB
Fits Get file →
Q4_K_S2.6 GB 4.2 GB
Fits Get file →
IQ4_NL2.7 GB 4.3 GB
Fits Get file →
Q4_K_M2.8 GB 4.4 GB
Fits Get file →
Q4_12.8 GB 4.4 GB
Fits Get file →
Q5_03.1 GB 4.7 GB
Fits Get file →
Q5_K_S3.1 GB 4.7 GB
Fits Get file →
Q5_K_M3.2 GB 4.8 GB
Fits Get file →
Q5_13.3 GB 4.9 GB
Fits Get file →
Q6_K3.6 GB 5.2 GB
Fits Get file →
Q8_04.6 GB 6.2 GB
Fits Get file →
BF168.7 GB 10.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (2.78 GB) or Q4_K_S (2.63 GB). If VRAM is limited to 6 GB, IQ4_XS (2.58 GB) or IQ2_M (1.49 GB) are good choices. For maximum quality and available RAM, Q6_K (3.56 GB) or Q8_0 (4.61 GB) provide near‑lossless performance.

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 Q3_K_M (2.3 GB file, about 3.9 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).
  • 12 GB VRAM: the best quant that fits is BF16 (8.7 GB file, about 10.3 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 Q1_0 at 1.1 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

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 byNANI-Nithin
FamilyFrognano
Licensemit
Downloads (HF)4,349
Last updated2026-10-04

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: Q1_0 is 1.1 GB, IQ1_S is 1.4 GB, IQ1_M is 1.5 GB, IQ2_XXS is 1.6 GB, Q2_0 is 1.6 GB, IQ2_XS is 1.7 GB and 24 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 NANI-Nithin/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 VRAM at 8 K context, which fits within 8 GB. Smaller quants like IQ2_M use around 3.1 GB.

Does the model support image input?

The GGUF runtime does not include vision support. The model card mentions vision, but the provided GGUF files are text‑only.

What context length does the model support?

The model supports up to approximately 131 K tokens of combined text and source code context.

Other GGUFs of FrogNano-4B-2609

Similar models

Browse all →

More from NANI-Nithin

All by NANI-Nithin →

More Frognano models

All Frognano →

Other small models

All small models →