# kanana-1.5-8b-instruct-2505-Persona-Merged by Hyungho Byun Source: https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merged-2 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve kanana-1.5-8b-instruct-2505-Persona-Merged (8B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 16.1 GB | 19.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 8.0 GB | 9.6 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 4.0 GB | 4.8 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 7, 2026. [kanana-1.5-8b-instruct-2505-Persona-Merged on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merged-2/gpus) ## Model Card By Hyungho Byun, published under apache-2.0, revision 40a8a8f9024f. This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. Read Hyungho Byun's full model card ### Uploaded finetuned model - Developed by: NotoriousH2 - License: apache-2.0 - Finetuned from model : kakaocorp/kanana-1.5-8b-instruct-2505 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. ## Configuration Architecture LlamaForCausalLM Context length (tokens) 32,768 Layers 32 Hidden size 4,096 Feed-forward size 14,336 Attention heads 32 Key/value heads 8 Head dimension 128 Vocabulary size 128,259 Stored precision bfloat16 Model type llama ## Identity and Version Repository NotoriousH2/kanana-1.5-8b-instruct-2505-Persona-Merged Publisher Hyungho Byun Task Text generation Modality Text Library transformers Parameters 8B parameters Languages en Revision 40a8a8f9024f8df1684beb2c1969471f318ac0c2 First published 2026-05-21 Last updated 2026-10-01 ## Files and Weights 13 files, 32.1 GB in total. The weights are 5 files totalling 32.1 GB in safetensors. Weights5 files · 32.1 GB Configuration3 files · 24.9 KB Tokenizer2 files · 17.3 MB Documentation1 file · 602 B Other1 file · 14.3 KB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model-00001-of-00004.safetensors | Weights | 4.9 GB | 9eb6b1b4312a | | model-00002-of-00004.safetensors | Weights | 4.9 GB | a3f6f2726132 | | model-00003-of-00004.safetensors | Weights | 4.9 GB | 407af2597b04 | | model-00004-of-00004.safetensors | Weights | 1.3 GB | 85e1f4ab43dd | | model.safetensors | Weights | 16.1 GB | a49a992662be | | config.json | Configuration | 777 B | — | | generation_config.json | Configuration | 170 B | — | | model.safetensors.index.json | Configuration | 23.9 KB | — | | README.md | Documentation | 602 B | — | | chat_template.jinja | Other | 14.3 KB | — | | .gitattributes | Repository | 1.6 KB | — | | tokenizer.json | Tokenizer | 17.2 MB | 31d17e500c82 | | tokenizer_config.json | Tokenizer | 66.3 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 32.1 GB [Download from Hyungho Byun](https://huggingface.co/NotoriousH2/kanana-1.5-8b-instruct-2505-Persona-Merged) Released by Hyungho Byun through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from kakaocorp/kanana-1.5-8b-instruct-2505 ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 32.1 GB | | 16-bit | 16.1 GB | | 8-bit | 8.0 GB | | 4-bit | 4.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About kanana-1.5-8b-instruct-2505-Persona-Merged ### How much GPU memory does kanana-1.5-8b-instruct-2505-Persona-Merged need? About 19.3 GB at 16-bit and 4.8 GB at 4-bit: the weights (8B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run kanana-1.5-8b-instruct-2505-Persona-Merged on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use kanana-1.5-8b-instruct-2505-Persona-Merged commercially? Yes. kanana-1.5-8b-instruct-2505-Persona-Merged is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### What is kanana-1.5-8b-instruct-2505-Persona-Merged's context length? 32,768 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text generation ### [kanana-1.5-8b-instruct-2505-Persona-Merge-K](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merge-k) [KIMsangen](https://savrn.com/model-publishers/egoigo) This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 8B parameters 32,768 tokens transformers [View model](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merge-k) Model · Text generation ### [kanana-1.5-8b-instruct-2505-Persona-Merged](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merged) [Jaehoon Song](https://savrn.com/model-publishers/luckysong777) This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 8B parameters 32,768 tokens transformers [View model](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merged) Model · Text generation ### [kanana-1.5-8b-instruct-2505-Persona-Merged](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merged-3) [Jihue](https://savrn.com/model-publishers/mgmbykai) This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 8B parameters 32,768 tokens transformers [View model](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merged-3) Model · Text generation ### [kanana-1.5-8b-instruct-2505-Persona-Merged](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merged-4) [Kihyun K](https://savrn.com/model-publishers/kihyun-k) This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 8B parameters 32,768 tokens transformers [View model](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merged-4) Model · Text generation ### [Llama-3.1-8B-Instruct](https://savrn.com/models/llama-3-1-8b-instruct) [Meta Llama](https://savrn.com/model-publishers/meta-llama) The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes (text in/text out). The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks. Model Architecture: Llama 3.1 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.… Access requested at publisher llama3.1 8B parameters transformers [View model](https://savrn.com/models/llama-3-1-8b-instruct) Model · Text generation ### [Llama-3.1-8B-Instruct-4bit](https://savrn.com/models/llama-3-1-8b-instruct-4bit) [MLX Community](https://savrn.com/model-publishers/mlx-community) The Model mlx-community/Llama-3.1-8B-Instruct-4bit was converted to MLX format from meta-llama/Llama-3.1-8B-Instruct using mlx-lm version 0.21.4. Open weights llama3.1 8B parameters 131,072 tokens mlx [View model](https://savrn.com/models/llama-3-1-8b-instruct-4bit) ## Hyungho Byun [All models and datasets](https://savrn.com/model-publishers/notorioush2) ## Versions - [40a8a8f9024f](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merged-2/versions/40a8a8f9024f) · current 2026-10-01 ## Explore More - [All text generation models](https://savrn.com/models/tasks/text-generation) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-01. - [Hugging Face record](https://huggingface.co/NotoriousH2/kanana-1.5-8b-instruct-2505-Persona-Merged) - [How the hub is built](https://savrn.com/model-hub/methodology)