Built from InclusionAI's original weights with our own importance matrix. The
calibration corpora
behind our builds are public.
Ling 3.0 Flash Fin is InclusionAI's finance-enhanced Ling model for research, valuation, spreadsheets, and long-horizon agent workflows.
These GGUFs are self-quantized from InclusionAI's original BF16 weights with our own importance matrix.
The repo currently includes BF16, AD-Q8_0, and AD-Q6_K builds; lower-bit quants are still uploading.
Ling 3.0 Flash Fin
, self-quantized to GGUF by
Atomic Chat
. It has 124B total parameters, activates 5.1B per token, and supports a 256K context window. The checkpoint extends Ling 3.0 Flash with continued training on high-quality financial data.
Highlights
End-to-end financial research:
connects retrieval, evidence review, calculation, modeling, and report preparation in one workflow.
Source-grounded search:
prioritizes authoritative sources and traceable answers. InclusionAI publishes
FinFIRST
for transparent evaluation.
Multi-document reasoning:
reconciles periods, definitions, assumptions, and conflicting figures across filings, earnings materials, and research.
Valuation and spreadsheet workflows:
understands formulas, estimate updates, cross-sheet dependencies, balance checks, and scenario analysis.
Research-ready output:
separates facts, analysis, judgments, and charts into material that can be reviewed and edited.
These GGUFs are
self-quantized from the original weights
, not a repack.
Thinking mode is enabled by default. InclusionAI recommends
temperature=1.0
,
top_p=0.95
, and
top_k=20
.
The chat template is embedded in the GGUF. Keep
--jinja
enabled so thinking mode and tool-call formatting are applied correctly.
Best practices
Parameter
Value
temperature
1.0
top_p
0.95
top_k
20
Allocate enough output length for research and agent tasks. Financial conclusions, valuation assumptions, and investment decisions still require professional review.
What the model is built for
The producer evaluates the model on FinFIRST, FinSearchComp Verified, FinCRAFT, Finance Agent, APEX-Agents, SpreadsheetBench, and tau3-Banking. These benchmarks cover source-grounded retrieval, investment research, long-horizon execution, valuation modeling, spreadsheet operations, and banking workflows.
See the
official model card
for the producer's benchmark results, deployment guidance, and limitations.
How these were made
Start from
inclusionAI/Ling-3.0-flash-Fin
, the original BF16 checkpoint.
Ling-3.0-flash-Fin-GGUF huggingface.co is an AI model on huggingface.co that provides Ling-3.0-flash-Fin-GGUF's model effect (), which can be used instantly with this AtomicChat Ling-3.0-flash-Fin-GGUF model. huggingface.co supports a free trial of the Ling-3.0-flash-Fin-GGUF model, and also provides paid use of the Ling-3.0-flash-Fin-GGUF. Support call Ling-3.0-flash-Fin-GGUF model through api, including Node.js, Python, http.
Ling-3.0-flash-Fin-GGUF huggingface.co is an online trial and call api platform, which integrates Ling-3.0-flash-Fin-GGUF's modeling effects, including api services, and provides a free online trial of Ling-3.0-flash-Fin-GGUF, you can try Ling-3.0-flash-Fin-GGUF online for free by clicking the link below.
AtomicChat Ling-3.0-flash-Fin-GGUF online free url in huggingface.co:
Ling-3.0-flash-Fin-GGUF is an open source model from GitHub that offers a free installation service, and any user can find Ling-3.0-flash-Fin-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of Ling-3.0-flash-Fin-GGUF install, users can directly use Ling-3.0-flash-Fin-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Ling-3.0-flash-Fin-GGUF install url in huggingface.co: