LLM EXPLORER 56,604 MODELS INDEXED

Q3 8B Ft Ep2 Merged by allura-forge

By allura-forge · 6 downloads
HF Repo ↗ Copy URL

Q3 8B Ft Ep2 Merged is an open-source language model by allura-forge. Features: 8b LLM, VRAM: 16.4GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.18.

  Arxiv:2505.09388   Conversational   Endpoints compatible   Q3   Quantized   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/allura-forge/q3-8b-ft-ep2-merged 

Q3 8B Ft Ep2 Merged Parameters and Internals

LLM NameQ3 8B Ft Ep2 Merged
Repository 🤗https://huggingface.co/allura-forge/q3-8b-ft-ep2-merged 
Model Size8b
Required VRAM16.4 GB
Updated2026-07-03
Maintainerallura-forge
Model Typeqwen3
Model Files  4.0 GB: 1-of-5   4.0 GB: 2-of-5   4.0 GB: 3-of-5   3.2 GB: 4-of-5   1.2 GB: 5-of-5
Quantization Typeq3
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.51.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Q3 8B Ft Ep2 Merged

Best Alternatives
Context / RAM
Downloads
Likes
BehChat SFTv2 Mixed Ckpt 6128K / 16.4 GB110
BehChat SFTv3 Ckpt1128K / 16.4 GB60
...0528 Qwen3 8B Unsloth Bnb 4bit128K / 7.5 GB445713
DeepSeek R1 0528 Qwen3 8B 4bit128K / 4.6 GB17816
...Seek R1 0528 Qwen3 8B Bnb 4bit128K / 6.1 GB9239
Qwen3 8B LQA 14e Full128K / 16.4 GB60
...Seek R1 0528 Qwen3 8B 4bit DWQ128K / 4.6 GB2128
...0528 Qwen3 8B Unsloth Bnb 4bit128K / 16.4 GB70
Annie Lite V0.2.9 Qwen3 8B80K / 16.4 GB50
Bonsai 8B Mlx 1bit64K / 1.3 GB9396221
Note: green Score (e.g. "73.2") means that the model is better than allura-forge/q3-8b-ft-ep2-merged.