LLM EXPLORER 60,645 MODELS INDEXED

Phi 3 Medium 128K Instruct GPTQ 8 Bit by bjaidi

By bjaidi · 5 downloads
HF Repo ↗ Copy URL

Phi 3 Medium 128K Instruct GPTQ 8 Bit is an open-source language model by bjaidi. Features: 14b LLM, VRAM: 14.6GB, Context: 128K, License: mit, Quantized, Instruction-Based, LLM Explorer Score: 0.13.

  8-bit   Conversational   Custom code   Endpoints compatible   Gptq   Instruct   Phi3   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/bjaidi/Phi-3-medium-128k-instruct-GPTQ-8-bit 

Phi 3 Medium 128K Instruct GPTQ 8 Bit Parameters and Internals

LLM NamePhi 3 Medium 128K Instruct GPTQ 8 Bit
Repository 🤗https://huggingface.co/bjaidi/Phi-3-medium-128k-instruct-GPTQ-8-bit 
Model Size14b
Required VRAM14.6 GB
Updated2026-08-07
Maintainerbjaidi
Model Typephi3
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.7 GB: 3-of-3
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typefloat16

Best Alternatives to Phi 3 Medium 128K Instruct GPTQ 8 Bit

Best Alternatives
Context / RAM
Downloads
Likes
...um 128K Instruct GPTQ 8 Bit C4128K / 14.6 GB60
... Medium 4K Instruct 8 Bit Gptq4K / 14.6 GB42
... Medium 4K Instruct 4 Bit Gptq4K / 7.7 GB60
Phi 3 Medium 4K Instruct 8bit4K / 14.3 GB51
Phi 3 Medium 128K Instruct128K / 28 GB45634389
...ess V2.5 Phi 3 Medium 128K 14B128K / 28 GB164
...i 3 Medium 128K Instruct C4 32128K / 15.5 GB50
Phi 3 Medium 128K Instruct AWQ128K / 7.8 GB141
Finetuned Phi3 Medium 128K128K / 28 GB80
Shisa V1 Phi3 14B128K / 28 GB52
Note: green Score (e.g. "73.2") means that the model is better than bjaidi/Phi-3-medium-128k-instruct-GPTQ-8-bit.