LLM EXPLORER 61,491 MODELS INDEXED

Nb Sau 7B 8K Step100k by NbAiLab

By NbAiLab · 5 downloads
HF Repo ↗ Copy URL

Nb Sau 7B 8K Step100k is an open-source language model by NbAiLab. Features: 7b LLM, VRAM: 13.5GB, Context: 4K, License: llama2, Quantized, LLM Explorer Score: 0.09.

Base model:finetune:meta-llama... Base model:meta-llama/llama-2-...   Endpoints compatible   Ext 8k   Ggml   Llama   Nb   Nn   No   Pytorch   Q4   Quantized   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/NbAiLab/nb-sau-7b-8k-step100k 

Nb Sau 7B 8K Step100k Parameters and Internals

Supported Languages 
primary (no, nn, nb), additional ()
LLM NameNb Sau 7B 8K Step100k
Repository 🤗https://huggingface.co/NbAiLab/nb-sau-7b-8k-step100k 
Base Model(s)  Llama 2 7B Hf   meta-llama/Llama-2-7b-hf
Model Size7b
Required VRAM13.5 GB
Updated2026-07-09
MaintainerNbAiLab
Model Typellama
Model Files  3.8 GB   10.0 GB: 1-of-2   3.5 GB: 2-of-2
Supported Languagesno nn nb
GGML QuantizationYes
Context Length8k
Quantization Typeggml|q4
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Padding Token[PAD]
Vocabulary Size32001
Torch Data Typefloat16

Best Alternatives to Nb Sau 7B 8K Step100k

Best Alternatives
Context / RAM
Downloads
Likes
Cria Llama2 7B V1.3 GGML4K / 3.8 GB530
Merak 7B V2 GGML4K / 2.9 GB56
Ennodata 7B2K / 13.5 GB14370
Smaugv0.1 6.0bpw H6 EXL2195K / 26.4 GB14
Smaugv0.1 5.0bpw H6 EXL2195K / 22.3 GB33
Smaugv0.1 4.65bpw H6 EXL2195K / 20.8 GB51
Smaugv0.1 4.0bpw H6 EXL2195K / 18 GB41
Smaugv0.1 8.0bpw H8 EXL2195K / 34.9 GB41
Smaugv0.1 3.0bpw H6 EXL2195K / 13.9 GB01
DeepSeek Prover V2 7B 4bit64K / 3.9 GB2364
Note: green Score (e.g. "73.2") means that the model is better than NbAiLab/nb-sau-7b-8k-step100k.