Q3 8B Kintsugi is an open-source language model by allura-org. Features: 8b LLM, VRAM: 16.4GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.2.
Autotrain compatible Axolotl Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-8b-base Conversational Dataset:ai2-adapt-dev/flan v2 ... Dataset:alfitaria/nemotron-ult... Dataset:allenai/tulu-3-if-augm... Dataset:allenai/tulu-3-sft-per... Dataset:antiven0m/physical-rea... Dataset:cognitivecomputations/... Dataset:freedomintelligence/me... Dataset:grimulkan/physical-rea... Dataset:grimulkan/theory-of-mi... Dataset:kalomaze/opus instruct... Dataset:nbeerbower/gutenberg-m... Dataset:nbeerbower/gutenberg2-... Dataset:nbeerbower/purpura-dpo Dataset:nobodyexistsontheinter... Dataset:nvidia/helpsteer3 Dataset:pocketdoc/dans-prosema... Dataset:pygmalionai/pippa Dataset:simplescaling/s1k-clau... Endpoints compatible Instruct Mergekit Q3 Quantized Qwen3 Region:us Roleplay Safetensors Sharded Tensorflow Unsloth
Model Card on HF 🤗: https://huggingface.co/allura-org/Q3-8B-Kintsugi
Q3 8B Kintsugi Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Q3 8B Kintsugi Parameters and Internals
| LLM Name | Q3 8B Kintsugi |
| Repository 🤗 | https://huggingface.co/allura-org/Q3-8B-Kintsugi |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 16.4 GB |
| Updated | 2025-11-01 |
| Maintainer | allura-org |
| Model Type | qwen3 |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | q3 |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.51.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
Best Alternatives to Q3 8B Kintsugi
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...epSeek R1 0528 Qwen3 8B Esper3 | 128K / 32.7 GB | 5 | 3 |
| ATLAS 8B Instruct | 40K / 16.4 GB | 17 | 2 |
| QVikhr 3 8B Instruction | 40K / 16.4 GB | 69 | 9 |
| Qwen3 8B ShiningValiant3 | 40K / 32.7 GB | 14 | 3 |
| Qwen3 8B Shadow FT BAAI 2K | 40K / 16.4 GB | 6 | 0 |
| Qwen3 8B Esper3 | 40K / 32.7 GB | 13 | 22 |
| Gradients Instruct 8B | 32K / 32.7 GB | 3 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than allura-org/Q3-8B-Kintsugi .
Rank the Q3 8B Kintsugi Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52832 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a