granite 4.1 8b fp8

Name: granite 4.1 8b fp8
Author: IBM

by IBM

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released April 2026131K context≈ 98,304 words

A compact, openly licensed model from IBM's Granite family, running in FP8 precision for efficient inference. With a 131K token context window, it handles long documents despite its 8B parameter size. The FP8 quantization means it runs faster and uses less memory than full-precision counterparts, with a modest trade-off in raw accuracy.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Factual Knowledge

Moderate

Multimodal

Use Case Fit

Fit scores are AI-generated based on model capabilities, intended use, and technical specifications. Learn more

granite 4.1 8b fp8

by IBM

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released April 2026131K context≈ 98,304 words

A compact, openly licensed model from IBM's Granite family, running in FP8 precision for efficient inference. With a 131K token context window, it handles long documents despite its 8B parameter size. The FP8 quantization means it runs faster and uses less memory than full-precision counterparts, with a modest trade-off in raw accuracy.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Factual Knowledge

Moderate

Multimodal

Use Case Fit

Fit scores are AI-generated based on model capabilities, intended use, and technical specifications. Learn more

Glossary

Context WindowThe maximum number of tokens a model can process in a single conversation or prompt.FP8 PrecisionA data format that stores numbers using 8 bits instead of the standard 32 bits, significantly reducing memory requirements with minimal quality loss.FP8 QuantizationA compression technique that reduces model size by representing weights using 8-bit floating-point numbers instead of higher precision, making it faster and more memory-efficient.Full-PrecisionA model using standard 32-bit floating-point numbers to represent weights, providing maximum accuracy but requiring more memory.InferenceThe process of running a trained model to generate predictions or outputs from new inputs.PrecisionThe level of numerical detail a model uses to represent its internal values; higher precision means more accurate calculations but requires more memory.QuantizationReducing a model's numerical precision (e.g., from 16-bit to 4-bit) to shrink memory usage and speed up inference.TokenA small unit of text (a word, subword, or punctuation mark) that a language model breaks input into for processing.