LLM EXPLORER 59,420 MODELS INDEXED

Tinyllama Singlish by mmpc

By mmpc · 6 downloads

Tinyllama Singlish is an open-source language model by mmpc. Features: LLM, VRAM: 2.2GB, Context: 2K, License: apache-2.0, Quantized, LLM Explorer Score: 0.13.

  4bit Base model:finetune:unsloth/ti... Base model:unsloth/tinyllama-b...   En   Endpoints compatible   Llama   Pytorch   Quantized   Region:us   Trl   Unsloth

Tinyllama Singlish Parameters and Internals

Model Type 
text-generation-inference, transformers, unsloth, llama, trl
Supported Languages 
en (unknown)
Training Details 
Methodology:
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
LLM NameTinyllama Singlish
Repository πŸ€—https://huggingface.co/mmpc/tinyllama-Singlish 
Base Model(s)  Tinyllama Bnb 4bit   unsloth/tinyllama-bnb-4bit
Required VRAM2.2 GB
Updated2026-04-24
Maintainermmpc
Model Typellama
Model Files  2.2 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Tinyllama Singlish

Best Alternatives
Context / RAM
Downloads
Likes
... Text Chat 512K 6.0bpw H6 EXL2512K / 5.2 GB61
... Text Chat 512K 5.0bpw H6 EXL2512K / 4.4 GB11
Slimorca Phi 3.5128K / 7.6 GB70
Phi 3.5 Instruct Vul128K / 7.6 GB170
... Text Chat 128K 6.0bpw H6 EXL2128K / 5.2 GB31
QuantumQuill16K / 2.2 GB50
Unsloth Phi 4 4bit16K / 8.3 GB1396
...ocalAI Functioncall Phi 4 V0.316K / 29.4 GB9110
...ocalAI Functioncall Phi 4 V0.316K / 29.4 GB68
PARM V2 Phi 4 4K CoT PyTorch16K / 29.4 GB01
Note: green Score (e.g. "73.2") means that the model is better than mmpc/tinyllama-Singlish.