Downloads · 30 days
1K
17% of all-time downloads
Qwen3006B-transcriber-beta
bingbangboom/Qwen3006B-transcriber-beta
Qwen3006B-transcriber-beta is a text generation model from bingbangboom. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Post processor for local ASR. - Developed by: bingbangboom - License: apache-2.0 - Finetuned from model : unsloth/qwen3-0.6b-unsloth-bnb-4bit
All-time downloads
6K
Public
Parameters
596M
3.9 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf2.7 GB · 69%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Mar 24, 2026
- Updated
- Mar 26, 2026
- SHA
- 2116621b
Try a prompt
Base models
Model card
From the Hugging Face model README
bingbangboom/Qwen3006B-transcriber-beta
Post processor for local ASR.
- Developed by: bingbangboom
- License: apache-2.0
- Finetuned from model : unsloth/qwen3-0.6b-unsloth-bnb-4bit
Recommended Settings
> Temperature = 0.1
> top_k = 10
> top_p = 0.95
> min_p = 0.05
> repeat_penalty = 1.0
> Prompt format (for chat) = {input transcript}
> Prompt format (for use in Handy) = ${output}
Note
No System Prompt required.
You need to disable thinking for the model by adding {%- set enable_thinking = false %} in the Jinja Prompt Template.
LMStudio: Go to model gallery, click the model entry, then in inference settings scroll to the bottom to Prompt Template and paste at top.
Available Model files:
Qwen3.5-0.8B.F16.ggufQwen3.5-0.8B.Q8_0.ggufQwen3.5-0.8B.Q5_K_M.gguQwen3.5-0.8B.Q4_K_M.ggufLora merged safetensor
This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Languages
- en
- Featherless Ai
- live
- Created
- Mar 24, 2026
- Updated
- Mar 26, 2026