Title: Falcon H1 0.5B Base vs Falcon H1 1.5B Deep Instruct %E2%80%94 LLM EU Canonical: https://llmeu.com/sl/compare/falcon-h1-0-5b-base-vs-falcon-h1-1-5b-deep-instruct/ Markdown mirror: https://llmeu.com/sl/compare/falcon-h1-0-5b-base-vs-falcon-h1-1-5b-deep-instruct.md Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json # Falcon H1 0.5B Base vs Falcon H1 1.5B Deep Instruct Postavite dva do %C5%A1tiri modele enega ob drugega glede na polja, ki odlo%C4%8Dajo o uvedbi: kontekst, cena, regija, licenca, jeziki, gostovanje in kaj je preverjeno. Kjer se dva modela razlikujeta, ta tabela poka%C5%BEe razliko in se ustavi. LLM EU ne objavi zna%C4%8Dke zmagovalca brez dokumentirane ocene za to nalogo, manjkajo%C4%8Da %C5%A1tevilka pa ostane manjkajo%C4%8Da, namesto da bi postala ni%C4%8D. ## Kdaj ga uporabiti ### [Falcon H1 0.5B Base](/sl/models/falcon-h1-0-5b-base/) #### Prednosti - open weights are published on Hugging Face and can be downloaded without a vendor agreement - at 0.5B parameters it fits on a single accelerator - the model page lists en #### Omejitve - catalogue only %E2%80%94 LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint - no evaluation has been run by LLM EU - the falcon-llm-license (other) licence is a custom agreement whose commercial terms were not established from its published text, so commercial serving is not permitted until a human clears it; the router must not route to it - the published configuration records no context window, so the card carries none - at 0.5B parameters, the weights fit on a single modest accelerator - a base checkpoint: it answers nothing useful without fine-tuning or a task head #### Naloge [Nizki stro%C5%A1ki](/sl/tasks/cheap/), [Ve%C4%8Djezi%C4%8Dna podpora](/sl/tasks/multilingual-support/) ### [Falcon H1 1.5B Deep Instruct](/sl/models/falcon-h1-1-5b-deep-instruct/) #### Prednosti - open weights are published on Hugging Face and can be downloaded without a vendor agreement - at 1.6B parameters it fits on a single accelerator - instruction-tuned checkpoint with a chat template in the repository #### Omejitve - catalogue only %E2%80%94 LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint - no evaluation has been run by LLM EU - the falcon-llm-license (other) licence is a custom agreement whose commercial terms were not established from its published text, so commercial serving is not permitted until a human clears it; the router must not route to it - the published configuration records no context window, so the card carries none - at 1.6B parameters, the weights fit on a single modest accelerator #### Naloge [Nizki stro%C5%A1ki](/sl/tasks/cheap/), [Ve%C4%8Djezi%C4%8Dna podpora](/sl/tasks/multilingual-support/), [Razmi%C5%A1ljanje](/sl/tasks/reasoning/) **Naloge:** [Nizki stro%C5%A1ki](/sl/tasks/cheap/), [Ve%C4%8Djezi%C4%8Dna podpora](/sl/tasks/multilingual-support/) ## Primerjaj modele - [Bloom 1b1 vs Falcon H1 1.5B Deep Instruct](/sl/compare/bloom-1b1-vs-falcon-h1-1-5b-deep-instruct/) - [Bloom 3B vs Falcon H1 1.5B Deep Instruct](/sl/compare/bloom-3b-vs-falcon-h1-1-5b-deep-instruct/) - [Bloom 560M vs Falcon H1 0.5B Base](/sl/compare/bloom-560m-vs-falcon-h1-0-5b-base/) - [Bloomz 560M vs Falcon H1 0.5B Base](/sl/compare/bloomz-560m-vs-falcon-h1-0-5b-base/) - [NVIDIA Cosmos Reason2 2B vs Falcon H1 1.5B Deep Instruct](/sl/compare/cosmos-reason2-2b-vs-falcon-h1-1-5b-deep-instruct/) - [DeepSeek R1 Distill Qwen 1.5B vs Falcon H1 1.5B Deep Instruct](/sl/compare/deepseek-r1-distill-qwen-1-5b-vs-falcon-h1-1-5b-deep-instruct/)