plamo-3-fin Guide: VRAM Requirements, GGUF Builds

September 26, 2026September 28, 2026

About This Model

PLaMo-3-610M-Fin-Instruct is a Japanese language model for the financial domain developed by Preferred Networks, Inc. It employs a causal decoder-only architecture with a BF16 tensor type and a context length of 262,144 tokens.

It was built by starting from the PLaMo-3 base model, performing continued pre-training using a financial corpus, followed by supervised fine-tuning (SFT) and direct preference optimization (DPO). The formatting conforms to the PLaMo-3 chat format.

What Makes It Stand Out

• It undergoes continued pre-training with a financial corpus, SFT, and DPO, enabling it to handle conversational tasks specialized for the financial domain.
• The context length is set to 262,144 tokens.
• The model’s responses include a reasoning block followed by the output answer.

Caveats and Weaknesses

• Because it is a small model, it retains less factual knowledge compared to larger models, and it is reported to be prone to hallucinations where it fluently outputs inaccurate text.
• At this model size, the reliability of safety alignment is low, and it may generate harmful content such as offensive or violent expressions.
• Since it is trained specialized for the financial domain, it is not a general-purpose assistant, and the outputs do not constitute legal, financial, tax, or investment advice.

Running It Locally

• The specified operating requirements include Python 3.10.0 or higher, numpy 1.26.4 or higher, numba 0.60.0 or higher, torch 2.6.0 to 2.9.0, transformers 5.0.0 or higher, and accelerate.
• When loading the model and tokenizer directly using Transformers, you must specify trust_remote_code=True.
• If you intend to use it outside the financial domain, it is recommended to evaluate it on your own tasks beforehand.
• License plamo-community-license: A custom license from the publisher. Check the original terms directly, including whether commercial use is permitted.

This license summary is not legal advice; check the original terms before use.

Sources: model cards for pfnet/plamo-3-610m-fin-instruct, as of 2026-09-26. This explanation was drafted by AI from those cards and checked by code and a second model before publication.

Our Coverage and Data

Everything Local Model Watch has published about the plamo-3-fin family: 1 article(s) covering the base model and its fine-tunes, plus converted builds we tracked after publication. Memory requirements below are computed by this site from file sizes, not quoted from model cards. Part of our model family index.

At a Glance

Hardware Requirements

Estimated requirements (calculated by Local Model Watch) — 890M parameters

Memory estimates add a 20% runtime overhead (KV cache, etc.) to the actual size of the distributed files. Actual usage varies with context length, batch size and inference engine. These figures are computed by this site from file sizes, not published by the model’s authors. File sizes are measured from the converted build mradermacher/plamo-3-610m-fin-instruct-GGUF. Compare with other models in our VRAM quick reference. What the quantization names mean: glossary.

Can You Run It Locally?

Runs in Ollama, LM Studio and llama.cpp via a converted build.

The publisher ships safetensors, but mradermacher/plamo-3-610m-fin-instruct-GGUF provides a GGUF build you can use.

License — other: A custom license from the publisher. Check the original terms directly, including whether commercial use is permitted.

Compiled by this site’s code from the published formats, converted builds we have found, and each engine’s own model registry. “Not found" means we have not seen such a build, not that none exists. License summaries are not legal advice — check the publisher’s original terms before relying on them.

Quantized and Converted Variants

File sizes of each build:

• Available builds in mradermacher/plamo-3-610m-fin-instruct-GGUF: Q2_K 0.4GB / Q3_K_S 0.4GB / Q3_K_M 0.5GB / Q3_K_L 0.5GB / IQ4_XS 0.5GB / Q4_K_S 0.5GB / Q4_K_M 0.5GB / Q5_K_S 0.6GB / Q5_K_M 0.6GB / Q6_K 0.7GB / Q8_0 0.9GB / F16 1.7GB

This section is appended automatically by Local Model Watch when a converted build of this model appears after publication. Memory figures are estimated from the size of the distributed files.

Articles (the family’s own models first, then newest)

Repositories

• pfnet/plamo-3-610m-fin-instruct

Last updated 2026-09-28 (JST). The explanation at the top of this page was written with the help of AI from the primary sources it cites. The tables and lists under “Our Coverage and Data" are assembled by code from our article log.