π§
Qwen3loop 0.6b Sft Deep Supervision V1 model by Lordnyx
β 41.7
π¬Technical Deep Dive
Full Specifications [+]
π Updated daily
Source summary: Based on Hugging Face metadata. Not a recommendation.
π‘οΈ Model Transparency Report
Technical metadata sourced from upstream repositories.
Open Metadata
π Identity & Source
- id
- hf-model--lordnyx--qwen3loop-0.6b-sft-deep-supervision-v1
- slug
- lordnyx--qwen3loop-0.6b-sft-deep-supervision-v1
- source
- huggingface
- author
- Lordnyx
- license
- Apache-2.0
- tags
- safetensors, gguf, qwen3loop, qwen, reasoning, deep-supervision, logic-puzzles, math, nanbeige-4.5, recurrent-transformer, text-generation, conversational, en, dataset:ianncity/glm-5.2-logic-puzzles, base_model:qwen/qwen2.5-0.5b-instruct, base_model:quantized:qwen/qwen2.5-0.5b-instruct, license:apache-2.0, endpoints_compatible, region:us, recursive-reasoning, loop-architecture, unrolled, simpo, anti-loop, hotfix-0.3, pt, agentic-sft, chain-of-thought, dynamic-depth
βοΈ Technical Specs
- architecture
- Qwen3LoopForCausalLM
- params billions
- 0.6
- context length
- 32,768
- pipeline tag
- text-generation
- vram gb
- 3
- vram is estimated
- true
- vram formula
- VRAM β (params * 0.75) + 2GB (KV) + 0.5GB (OS)
π Engagement & Metrics
- downloads
- 2,085
Data indexed from public sources. Updated daily.