LLM EXPLORER 59,420 MODELS INDEXED

PrimaSumika 10.7B 128K by xxx777xxxASD

By xxx777xxxASD · 3 downloads

PrimaSumika 10.7B 128K is an open-source language model by xxx777xxxASD. Features: 10.7b LLM, VRAM: 21.5GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.11.

  Conversational   En   Endpoints compatible   Merge   Mistral   Moe   Region:us   Safetensors   Sharded   Tensorflow

PrimaSumika 10.7B 128K Parameters and Internals

Model Type 
merge, moe
Additional Notes 
Test 'sandwich' merge configuration.
Supported Languages 
en (proficient)
LLM NamePrimaSumika 10.7B 128K
Repository πŸ€—https://huggingface.co/xxx777xxxASD/PrimaSumika-10.7B-128k 
Model Size10.7b
Required VRAM21.5 GB
Updated2026-07-24
Maintainerxxx777xxxASD
Model Typemistral
Model Files  10.0 GB: 1-of-3   9.9 GB: 2-of-3   1.6 GB: 3-of-3
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to PrimaSumika 10.7B 128K

Best Alternatives
Context / RAM
Downloads
Likes
Barely Regal 10.7B32K / 21.5 GB190
Quintellect 10.7B32K / 21.4 GB223
Chikuma 10.7B32K / 21.4 GB1315
PiVoT 10.7B Mistral V0.232K / 21.4 GB765
Longcat 10.7B32K / 21.5 GB83
Multi Verse Model 10.7B32K / 21.5 GB21
... Loyal Mistral Maid 32K V0.2 A32K / 21.5 GB31
Chikuma 10.7B V232K / 21.4 GB100
PiVoT 10.7B Mistral V0.2 RP32K / 21.4 GB677
Mark1 Revision 10.7B32K / 42.9 GB161
Note: green Score (e.g. "73.2") means that the model is better than xxx777xxxASD/PrimaSumika-10.7B-128k.