PFN Open-Sources PLaMo 3.0 Fin: an 8B Japanese Finance Model with Japanese Reasoning and Tool Calling, Scoring 55.8 on a Japanese Finance Benchmark Ahead of Gemma 4 E4B and gpt-oss-20b, Fine-Tuned on In-House MN-Core 2 Chips
Japan's Preferred Networks (PFN) released PLaMo 3.0 Fin (plamo-3-8b-fin-instruct) on Hugging Face on November 9 under the PLaMo Community License. Built on PLaMo 3 NICT 8B Base, co-developed with NICT, it went through continued pre-training on finance corpora, SFT and DPO. It writes its reasoning in Japanese before answering, supports OpenAI-style function calling and can run on a single GPU in private clouds or on-premises. Per PFN, its average on the Japanese finance benchmark japanese-lm-fin-harness rose from 48.0 to 55.8, ahead of Gemma 4 E4B (45.6) and gpt-oss-20b (43.0) but behind Qwen3.5-9B (60.1) and Ministral 3 14B (62.8). SFT ran on PFN's in-house MN-Core 2 AI chip, and a coding agent helped port the training code in under a week.
Key Takeaways
- Specs (per PFN): 8B parameters, base PLaMo 3 NICT 8B Base, 262,144-token context (finance continued pre-training used 32,768-token sequences), BF16, Japanese-focused
- japanese-lm-fin-harness: 48.0 to 55.8; 64.9 on the securities sales rep exam task, 14 points above Qwen3.5-9B; CPA audit task up from 13.1 to 29.2
- pfmt-bench-fin-ja multi-turn finance chat: 8.35 (Qwen3.5-9B 8.53, Ministral 3 14B 8.11, gpt-oss-20b 7.83); PFN's own finance tool-use benchmark: 71.3 (Gemma 4 E4B 76.2, Qwen3.5-9B 75.4)
- Tool use: only 0.9% of samples answered without calling any tool (Gemma 4 E4B 10.7%) and it reached the tool holding the needed data 78.9% of the time; PFN warns that reasoning can run too long when many tools are offered
- License: PLaMo Community License, free commercial use (with registration) for companies and individuals under JPY 1 billion in annual revenue; vLLM 0.32.0+ ships plamo3 reasoning and tool-call parsers
