LLM EXPLORER 60,645 MODELS INDEXED

Phi 4K Gsm8k by acbdkk

By acbdkk · 10 downloads
HF Repo ↗ Copy URL

Phi 4K Gsm8k is an open-source language model by acbdkk. Features: 3.9b LLM, VRAM: 2.3GB, Context: 4K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.13.

  4-bit   4bit   Bitsandbytes   Conversational   En   Endpoints compatible   Instruct   Mistral   Quantized   Region:us   Safetensors   Sft   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/acbdkk/phi-4k-gsm8k 

Phi 4K Gsm8k Parameters and Internals

Model Type 
text-generation-inference
Additional Notes 
Finetuned from model: unsloth/phi-3-mini-4k-instruct-bnb-4bit
Supported Languages 
en (proficient)
Training Details 
Methodology:
Trained 2x faster with Unsloth and Huggingface's TRL library
LLM NamePhi 4K Gsm8k
Repository 🤗https://huggingface.co/acbdkk/phi-4k-gsm8k 
Base Model(s)  unsloth/phi-3-mini-4k-instruct-bnb-4bit   unsloth/phi-3-mini-4k-instruct-bnb-4bit
Model Size3.9b
Required VRAM2.3 GB
Updated2026-08-06
Maintaineracbdkk
Model Typemistral
Instruction-BasedYes
Model Files  2.3 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
Vocabulary Size32064
Torch Data Typefloat16

Best Alternatives to Phi 4K Gsm8k

Best Alternatives
Context / RAM
Downloads
Likes
...hi 3 Mini 4K Instruct Bnb 4bit4K / 2.3 GB1697346
...3 Mini 4K Instruct V0 Bnb 4bit4K / 2.3 GB133
Phi 3 Autocomplete Search4K / 2.3 GB50
Small Mistral 14K / 2.3 GB50
Hf4K / 2.3 GB120
MediChat Medium4K / 2.3 GB61
Recophi3 4bit4K / 2.3 GB60
Phi3 MeetingQA 4bit4K / 2.3 GB60
...Spydaz Web AI ChatQA 002 4 BIT512K / 4.1 GB240
Spydaz Web AI 02 4 BIT32K / 4.1 GB280
Note: green Score (e.g. "73.2") means that the model is better than acbdkk/phi-4k-gsm8k.