Phi 3 Mini 128K Instruct Abliterated V3 AWQ is an open-source language model by vaclavkosar. Features: 3.8b LLM, VRAM: 2.3GB, Context: 128K, License: mit, Quantized, Instruction-Based, LLM Explorer Score: 0.13.
4-bit Awq Conversational Custom code Endpoints compatible Instruct Phi3 Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/vaclavkosar/Phi-3-mini-128k-instruct-abliterated-v3-AWQ
Phi 3 Mini 128K Instruct Abliterated V3 AWQ 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)
Phi 3 Mini 128K Instruct Abliterated V3 AWQ Parameters and Internals
| LLM Name | Phi 3 Mini 128K Instruct Abliterated V3 AWQ |
| Repository 🤗 | https://huggingface.co/vaclavkosar/Phi-3-mini-128k-instruct-abliterated-v3-AWQ |
| Model Size | 3.8b |
| Required VRAM | 2.3 GB |
| Updated | 2026-04-22 |
| Maintainer | vaclavkosar |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | Phi3ForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.41.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | float16 |
Best Alternatives to Phi 3 Mini 128K Instruct Abliterated V3 AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Flow Judge V0.1 AWQ | 128K / 2.3 GB | 4138 | 6 |
| ... 3 Mini 128K Instruct AWQ 4bit | 128K / 2.3 GB | 11 | 2 |
| Phi 3 Mini 128K Instruct AWQ | 128K / 2.3 GB | 25 | 3 |
| Ph3 Q8 | 128K / 4 GB | 7 | 0 |
| ...hi 3 Mini 4K Instruct Sft 4bit | 4K / 2.3 GB | 5 | 0 |
| Phi 3.5 Mini Instruct | 128K / 7.7 GB | 701846 | 980 |
| Phi 4 Mini Instruct Heretic | 128K / 7.7 GB | 47 | 0 |
| Phi 3 Mini 128K Instruct | 128K / 7.7 GB | 5 | 0 |
| MediPhi Instruct | 128K / 7.7 GB | 1704 | 67 |
| NuExtract V1.5 | 128K / 7.7 GB | 108511 | 89 |
Note: green Score (e.g. "73.2") means that the model is better than vaclavkosar/Phi-3-mini-128k-instruct-abliterated-v3-AWQ .
Rank the Phi 3 Mini 128K Instruct Abliterated V3 AWQ 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? 53999 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