RI

Riverfish Rocinante 12B SFT

RiverfishGGUF by amylynnUpdated 2026-07-26
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant6.1 GB
Quick answer

Riverfish Rocinante 12B SFT needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 6.1 GB (Q3_K_M) to 7.5 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Riverfish Rocinante 12B SFT is a 12.2B-parameter Riverfish model in GGUF format, quantized by amylynn. Its trained context length is 1000K tokens. The repository has 2 quant files, from 6.1 GB (Q3_K_M) to 7.5 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M6.1 GB 7.9 GB
Tight Get file →
Q4_K_M7.5 GB 9.3 GB
Too big Get file →

What GPU do you need for Riverfish Rocinante 12B SFT?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q3_K_M (6.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (7.5 GB file, about 9.3 GB in use).

Which Riverfish Rocinante 12B SFT quant should you choose?

Q4_K_M is the usual starting point for Riverfish Rocinante 12B SFT: it balances file size and quality well. Here it is a 7.5 GB file.

If memory is tight, the smallest file is Q3_K_M at 6.1 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

Architecturellama
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized byamylynn
FamilyRiverfish
Licenseapache-2.0
Downloads (HF)15
Last updated2026-07-26

Frequently asked questions about Riverfish Rocinante 12B SFT

How much VRAM does Riverfish Rocinante 12B SFT need?

About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 Riverfish Rocinante 12B SFT on an 8 GB GPU?

Yes, with Q3_K_M: the 6.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Riverfish Rocinante 12B SFT GGUF?

It depends on the quant: Q3_K_M is 6.1 GB, Q4_K_M is 7.5 GB.

What context length does Riverfish Rocinante 12B SFT support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Riverfish Rocinante 12B SFT GGUF?

The files are on Hugging Face in the amylynn/Riverfish-Rocinante-12B-SFT-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 Riverfish Rocinante 12B SFT 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 Riverfish-Rocinante-12B

Similar models

Browse all →

More from amylynn

All by amylynn →

More Riverfish models

All Riverfish →

Other medium models

All medium models →