FrogNano 4B 2609 Pollard needs about 3.7 GB of memory at IQ3_S (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.4 GB to 3.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.
FrogNano 4B 2609 Pollard – a compact, code‑focused LLM with vision support
FrogNano 4B 2609 Pollard is a 4.33 billion‑parameter model derived from Qwen3.5‑4B. It is post‑trained for repository‑level software engineering and includes vision capabilities. The model supports a combined context length of approximately 131 K tokens.
Good at
- Repository‑level code debugging
- Multimodal vision tasks
- Long‑context reasoning
Limits
- No vision support in standard GGUF rungs
- Requires ik_llama.cpp for IQ2_KT
- Large VRAM needed for higher‑fidelity rungs
Best for
- Codebase navigation
- Patch generation with Leaf harness
- Multimodal instruction following
Who it’s for. Developers and researchers needing a lightweight LLM for software engineering tasks. The model is suitable for environments where GPU memory is limited but long‑context and vision support are required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 1.4 GB | 3.0 GB | Fits | Get file → | |
| IQ3_S | 2.1 GB | 3.7 GB | Fits | Get file → | |
| IQ4_XS | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q6_K | 3.6 GB | 5.2 GB | Fits | Get file → |
For ~5.6 GB RAM/VRAM use Q6_K (3.56 GB). For ~4.5 GB use IQ4_XS (2.48 GB). For ~4.1 GB use IQ3_S (2.06 GB). For ~3.4 GB use IQ2_KT (1.42 GB) with ik_llama.cpp. Memory estimates are approximate.
What GPU do you need for FrogNano 4B 2609 Pollard?
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_S (2.1 GB file, about 3.7 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 Pollard quant should you choose?
IQ3_S (2.1 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is the first one in the table at 1.4 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
Source
Frequently asked questions about FrogNano 4B 2609 Pollard
How much VRAM does FrogNano 4B 2609 Pollard need?
About 3.7 GB at IQ3_S with an 8K context window. That is the 2.1 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 Pollard 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 Pollard GGUF?
It depends on the quant: file is 1.4 GB, IQ3_S is 2.1 GB, IQ4_XS is 2.5 GB, Q6_K is 3.6 GB.
What context length does FrogNano 4B 2609 Pollard 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 Pollard GGUF?
The files are on Hugging Face in the PollardWeights/FrogNano-4B-2609-Pollard 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 Pollard 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 Pollard on 8 GB VRAM?
Yes, the Q6_K quant (3.56 GB) fits comfortably in 8 GB VRAM with room for context.
Does the model support vision tasks?
Yes, the model has detected vision abilities, but standard GGUF rungs may require special handling.
What license does the model use?
The model is released under the MIT license.