LLM EXPLORER 68,292 MODELS INDEXED

GPT Distill Qwen3 8B Spellguard SLERP by ITLL

By ITLL · 47 downloads

GPT Distill Qwen3 8B Spellguard SLERP is an open-source language model by ITLL. Features: 8b LLM, VRAM: 16.4GB, Context: 40K, License: apache-2.0, Instruction-Based, Merged.

  Merged Model   Ai-agents Base model:jackrong/gpt-distil... Base model:spellguard/spellgua...   Chain-of-thought   Content-moderation   Conversational Dataset:3nesdeniz/agentic-prom...   Dataset:allenai/wildchat-1m   Dataset:allenai/wildguardmix   Dataset:allenai/wildjailbreak   Dataset:bench-llm/or-bench   Dataset:bigcode/commitpackft   Dataset:coherelabs/aya dataset Dataset:deepset/prompt-injecti... Dataset:glaiveai/glaive-functi... Dataset:huggingfacefw/fineweb-... Dataset:interstellarninja/tool... Dataset:jackhhao/jailbreak-cla... Dataset:jackrong/chinese-qwen3... Dataset:jackrong/gpt-oss-120b-... Dataset:jackrong/natural-reaso... Dataset:jackrong/sharegpt-gpt-... Dataset:jailbreakv-28k/jailbre... Dataset:lakera/gandalf ignore ... Dataset:microsoft/llmail-injec... Dataset:neuralchemy/prompt-inj... Dataset:nvidia/aegis-ai-conten... Dataset:nvidia/nemotron-rl-age... Dataset:nvidia/nemotron-rl-jai...   Dataset:openassistant/oasst2 Dataset:rgeada/tool-response-i... Dataset:s-labs/prompt-injectio...   Endpoints compatible   Generated from trainer   Guardrail   Instruct   Jailbreak-detection   Prompt-injection   Qwen   Qwen3   Reasoning   Region:us   Safetensors   Safety   Sft   Sharded   Tensorflow   Unsloth

GPT Distill Qwen3 8B Spellguard SLERP Parameters and Internals

LLM NameGPT Distill Qwen3 8B Spellguard SLERP
Repository πŸ€—https://huggingface.co/ITLL/GPT-Distill-Qwen3-8B-Spellguard-SLERP 
Base Model(s)  GPT Distill Qwen3 8B Thinking   Spellguard/Spellguard-1.0-8B   Jackrong/GPT-Distill-Qwen3-8B-Thinking   Spellguard/Spellguard-1.0-8B
Merged ModelYes
Model Size8b
Required VRAM16.4 GB
Updated2026-11-22
MaintainerITLL
Model Typeqwen3
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   1.6 GB: 4-of-4
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version5.23.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to GPT Distill Qwen3 8B Spellguard SLERP

Best Alternatives
Context / RAM
Downloads
Likes
DeepAnalyze 8B128K / 16.4 GB51293
...epSeek R1 0528 Qwen3 8B Esper3128K / 32.7 GB153
Polyedit Qwen3 8B Property V140K / 32.7 GB2351
Wolof Qwen3 8B V261040K / 16.4 GB1151
WebWorld 8B40K / 16.4 GB95064
WebWorld 32B40K / 65.8 GB34275
...nBias Plus SFT Instruct Legacy40K / 16.4 GB3831
WebWorld 14B40K / 29.5 GB50428
...n3 8B UnBias Plus SFT Instruct40K / 16.4 GB541
QVikhr 3 8B Instruction40K / 16.4 GB384610
Note: green Score (e.g. "73.2") means that the model is better than ITLL/GPT-Distill-Qwen3-8B-Spellguard-SLERP.