Open-weight model
kanana-1.5-8b-instruct-2505-Persona-GGUF
by Hyungho Byun NotoriousH2/kanana-1.5-8b-instruct-2505-Persona-GGUF
kanana-1.5-8b-instruct-2505-Persona-GGUF is an open-weight model from Hyungho Byun. It has 32,768-token context. Its published files total 4.9 GB. It draws 201 downloads a month.
This model was finetuned and converted to GGUF format using Unsloth. - kanana-1.5-8b-instruct-2505.Q4KM.gguf This was trained 2x faster with Unsloth
Model Card
This model was finetuned and converted to GGUF format using Unsloth. - kanana-1.5-8b-instruct-2505.Q4KM.gguf This was trained 2x faster with Unsloth
Excerpt from the card by Hyungho Byun.
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-GGUF
- Publisher
- Hyungho Byun
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- d8c5a76c4d12ab618c05ccf5d46869c2e130aa29
- First published
- 2026-09-03
- Last updated
- 2026-10-01
Files and Weights
4 files, 4.9 GB in total. The weights are 1 file totalling 4.9 GB in gguf.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| kanana-1.5-8b-instruct-2505.Q4_K_M.gguf | Weights | 4.9 GB | 616f2a6c8b22 |
| config.json | Configuration | 777 B | — |
| README.md | Documentation | 747 B | — |
| .gitattributes | Repository | 1.6 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 4.9 GB
Released by Hyungho Byun through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 4.9 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-GGUF
What is kanana-1.5-8b-instruct-2505-Persona-GGUF's context length?
32,768 tokens, from the maximum position embeddings in its published configuration.