FA

Fat_Fish

FatGGUF by mradermacherUpdated 2026-03-12
Download on Hugging Face
Parameters16.6B
Context128K
Layers56
Architecturellama
Smallest quant0.0 GB
Quick answer

Fat_Fish needs about 14.0 GB of memory at Q4_K_M (a 10.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 25 quants, from 0.0 GB to 14.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 11.3 GB.

Fat_Fish is a 16.6B-parameter Fat model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 25 quant files, from 0.0 GB to 14.5 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.3 GB
Fits Get file →
IQ1_S5.3 GB 8.6 GB
Too big Get file →
IQ1_M5.5 GB 8.8 GB
Too big Get file →
IQ2_XXS5.9 GB 9.2 GB
Too big Get file →
IQ2_XS6.2 GB 9.5 GB
Too big Get file →
IQ2_S6.5 GB 9.8 GB
Too big Get file →
Q2_K_S6.8 GB 10.1 GB
Too big Get file →
IQ2_M6.8 GB 10.1 GB
Too big Get file →
Q2_K6.9 GB 10.2 GB
Too big Get file →
IQ3_XXS7.3 GB 10.6 GB
Too big Get file →
IQ3_XS7.6 GB 10.9 GB
Too big Get file →
Q3_K_S7.9 GB 11.2 GB
Too big Get file →
IQ3_S7.9 GB 11.3 GB
Too big Get file →
IQ3_M8.2 GB 11.5 GB
Too big Get file →
Q3_K_M8.6 GB 12.0 GB
Too big Get file →
Q3_K_L9.1 GB 12.4 GB
Too big Get file →
IQ4_XS9.2 GB 12.5 GB
Too big Get file →
Q4_09.5 GB 12.9 GB
Too big Get file →
IQ4_NL9.6 GB 12.9 GB
Too big Get file →
Q4_K_S10.0 GB 13.3 GB
Too big Get file →
Q4_110.5 GB 13.8 GB
Too big Get file →
Q4_K_M10.7 GB 14.0 GB
Too big Get file →
Q5_K_S11.7 GB 15.1 GB
Too big Get file →
Q5_K_M12.3 GB 15.6 GB
Too big Get file →
Q6_K14.5 GB 17.8 GB
Too big Get file →

What GPU do you need for Fat_Fish?

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 the main file (0.0 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.3 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q3_K_M (8.6 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (12.3 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (14.5 GB file, about 17.8 GB in use).

Which Fat_Fish quant should you choose?

Q4_K_M is the usual starting point for Fat_Fish: it balances file size and quality well. Here it is a 10.7 GB file.

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

Architecturellama
Parameters16.6B
Layers56
Trained context131,072 tokens
KV cache (fp16)336 KB per token

Source

Quantized bymradermacher
FamilyFat
Licenseapache-2.0
Downloads (HF)190
Last updated2026-03-12

Frequently asked questions about Fat_Fish

How much VRAM does Fat_Fish need?

About 14.0 GB at Q4_K_M with an 8K context window. That is the 10.7 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 Fat_Fish on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Fat_Fish GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 5.3 GB, IQ1_M is 5.5 GB, IQ2_XXS is 5.9 GB, IQ2_XS is 6.2 GB, IQ2_S is 6.5 GB and 19 more.

What context length does Fat_Fish support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.8 GB at 8K and 11.3 GB at 32K.

Where can I download Fat_Fish GGUF?

The files are on Hugging Face in the mradermacher/Fat_Fish-i1-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 Fat_Fish 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.

Other GGUFs of Fat_Fish

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Fat models

All Fat →

Other medium models

All medium models →