LLM EXPLORER 60,783 MODELS INDEXED

Tess 70B V1.6 Marlin by qeternity

By qeternity · 7 downloads
HF Repo ↗ Copy URL

Tess 70B V1.6 Marlin is an open-source language model by qeternity. Features: 70b LLM, VRAM: 36.3GB, Context: 31K, Quantized, LLM Explorer Score: 0.11.

  4-bit   Autotrain compatible   Conversational   Endpoints compatible   Gptq   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/qeternity/Tess-70B-v1.6-Marlin 

Tess 70B V1.6 Marlin Parameters and Internals

LLM NameTess 70B V1.6 Marlin
Repository 🤗https://huggingface.co/qeternity/Tess-70B-v1.6-Marlin 
Model Size70b
Required VRAM36.3 GB
Updated2024-12-02
Maintainerqeternity
Model Typellama
Model Files  36.3 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Context Length32764
Model Max Length32764
Transformers Version4.39.1
Tokenizer ClassLlamaTokenizer
Padding Token[PAD]
Vocabulary Size32001
Torch Data Typefloat16

Best Alternatives to Tess 70B V1.6 Marlin

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB5176
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB1290
...ama 3.1 70B Instruct Gptq 4bit128K / 39.9 GB74
Opus V1.2 70B Marlin32K / 36.4 GB80
MoMo 70B Lora 1.8.4 DPO GPTQ32K / 41.3 GB51
MoMo 70B Lora 1.8.6 DPO GPTQ32K / 41.3 GB41
Midnight Miqu 70B V1.5 GPTQ32G31K / 40.7 GB434
...Midnight Miqu 70B V1.0 GPTQ32G31K / 40.7 GB82
Senku 70B GPTQ 4bit31K / 36.7 GB61
Miqu 1 70B Sf GPTQ31K / 40.7 GB21
Note: green Score (e.g. "73.2") means that the model is better than qeternity/Tess-70B-v1.6-Marlin.