LLM EXPLORER 59,420 MODELS INDEXED

Deepseek Ai DeepSeek R1 Distill Llama 70B 4.25bpw H6 EXL2 by MikeRoz

By MikeRoz · 10 downloads
HF Repo ↗ Copy URL

Deepseek Ai DeepSeek R1 Distill Llama 70B 4.25bpw H6 EXL2 is an open-source language model by MikeRoz. Features: 70b LLM, VRAM: 39.4GB, Context: 128K, Quantized, LLM Explorer Score: 0.16.

  Exl2   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/MikeRoz/deepseek-ai_DeepSeek-R1-Distill-Llama-70B-4.25bpw-h6-exl2 

Deepseek Ai DeepSeek R1 Distill Llama 70B 4.25bpw H6 EXL2 Parameters and Internals

LLM NameDeepseek Ai DeepSeek R1 Distill Llama 70B 4.25bpw H6 EXL2
Repository 🤗https://huggingface.co/MikeRoz/deepseek-ai_DeepSeek-R1-Distill-Llama-70B-4.25bpw-h6-exl2 
Model Size70b
Required VRAM39.4 GB
Updated2026-08-04
MaintainerMikeRoz
Model Typellama
Model Files  8.6 GB: 1-of-5   8.6 GB: 2-of-5   8.6 GB: 3-of-5   8.5 GB: 4-of-5   5.1 GB: 5-of-5
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.47.0.dev0
Tokenizer ClassLlamaTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<｜end▁of▁sentence｜>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Deepseek Ai DeepSeek R1 Distill Llama 70B 4.25bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB415
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB253
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB252
...0B Instruct Gradient 262K 4bit256K / 39.7 GB253
...0B Instruct Gradient 262K 8bit256K / 75 GB262
...0B Instruct Gradient 262K 2bit256K / 21.9 GB201
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB80
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB71
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB60
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB60