LLM EXPLORER 63,407 MODELS INDEXED

BigWeave V20 110B by llmixer

By llmixer · 51 downloads
HF Repo ↗ Copy URL

BigWeave V20 110B is an open-source language model by llmixer. Features: 110b LLM, VRAM: 220GB, Context: 4K, License: unknown, LLM Explorer Score: 0.12, Arc: 68.2, HellaSwag: 88.5, MMLU: 70.5, GSM8K: 36.4.

  110b   Conversational   En   Endpoints compatible   Frankenmerge   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/llmixer/BigWeave-v20-110b 

BigWeave V20 110B Parameters and Internals

Model Type 
frankenmerge, conversational
Additional Notes 
This model is a merge of two models: 152334H/miqu-1-70b-sf and lizpreciatior/lzlv_70b_fp16_hf.
LLM NameBigWeave V20 110B
Repository 🤗https://huggingface.co/llmixer/BigWeave-v20-110b 
Model Size110b
Required VRAM220 GB
Updated2026-08-07
Maintainerllmixer
Model Typellama
Model Files  9.8 GB: 1-of-23   9.9 GB: 2-of-23   9.8 GB: 3-of-23   10.0 GB: 4-of-23   10.0 GB: 5-of-23   9.8 GB: 6-of-23   9.8 GB: 7-of-23   9.9 GB: 8-of-23   10.0 GB: 9-of-23   9.6 GB: 10-of-23   9.8 GB: 11-of-23   9.8 GB: 12-of-23   9.8 GB: 13-of-23   9.9 GB: 14-of-23   9.8 GB: 15-of-23   9.9 GB: 16-of-23   10.0 GB: 17-of-23   9.8 GB: 18-of-23   10.0 GB: 19-of-23   9.8 GB: 20-of-23   10.0 GB: 21-of-23   9.8 GB: 22-of-23   3.0 GB: 23-of-23
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseunknown
Context Length4096
Model Max Length4096
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to BigWeave V20 110B

Best Alternatives
Context / RAM
Downloads
Likes
TinyBalls 110M V132K / 0.5 GB3141
...10M Experimental V0.1 Instruct1K / 0.2 GB361
HelpingAI 110M1K / 0.2 GB5082
Tinybooks 110M Idiot Iter10001K / 0.4 GB60
TinyStoriesChinese 110M1K / 0.4 GB51
Tinyllama 110M Fp321K / 0.4 GB14800
Llama 110M1K / 0.2 GB110
Tinyllama 110M1K / 0.2 GB8666
Note: green Score (e.g. "73.2") means that the model is better than llmixer/BigWeave-v20-110b.