LLM EXPLORER 59,358 MODELS INDEXED

DeepSeek R1 Distill Llama 70B 3bit by mlx-community

By mlx-community · 288 downloads
HF Repo ↗ Copy URL

DeepSeek R1 Distill Llama 70B 3bit is an open-source language model by mlx-community. Features: 70b LLM, VRAM: 30.8GB, Context: 128K, Quantized, LLM Explorer Score: 0.17.

  3-bit   3bit Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Conversational   Endpoints compatible   Llama   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/DeepSeek-R1-Distill-Llama-70B-3bit 

DeepSeek R1 Distill Llama 70B 3bit Parameters and Internals

LLM NameDeepSeek R1 Distill Llama 70B 3bit
Repository 🤗https://huggingface.co/mlx-community/DeepSeek-R1-Distill-Llama-70B-3bit 
Base Model(s)  DeepSeek R1 Distill Llama 70B   deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Model Size70b
Required VRAM30.8 GB
Updated2026-07-21
Maintainermlx-community
Model Typellama
Model Files  5.4 GB: 1-of-6   5.4 GB: 2-of-6   5.3 GB: 3-of-6   5.3 GB: 4-of-6   5.3 GB: 5-of-6   4.1 GB: 6-of-6
Quantization Type3bit
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.47.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<｜end▁of▁sentence｜>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to DeepSeek R1 Distill Llama 70B 3bit

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