CoolFace
Modelpublic

prithivMLmods/Lambda-Equulei-1.5B-xLingual-GGUF

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes591downloads
Model Card

Lambda-Equulei-1.5B-xLingual

Lambda-Equulei-1.5B-xLingual is a multilingual conversational model fine-tuned from Qwen2-1.5B, specifically designed for cross-lingual chat and experimental conversations across 30+ languages. It brings advanced multilingual understanding and natural dialogue capabilities in a compact size, ideal for international communication tools, language learning platforms, and global conversational assistants. ## Model Files
FilenameSizeFormatDescription
Lambda-Equulei-1.5B-xLingual.BF16.gguf3.56 GBBF16Brain Float 16-bit quantization
Lambda-Equulei-1.5B-xLingual.F16.gguf3.56 GBF16Half precision (16-bit) floating point
Lambda-Equulei-1.5B-xLingual.F32.gguf7.11 GBF32Full precision (32-bit) floating point
Lambda-Equulei-1.5B-xLingual.Q2_K.gguf753 MBQ2_K2-bit quantization with K-quant
Lambda-Equulei-1.5B-xLingual.Q3KL.gguf980 MBQ3KL3-bit quantization (Large) with K-quant
Lambda-Equulei-1.5B-xLingual.Q3KM.gguf924 MBQ3KM3-bit quantization (Medium) with K-quant
Lambda-Equulei-1.5B-xLingual.Q3KS.gguf861 MBQ3KS3-bit quantization (Small) with K-quant
Lambda-Equulei-1.5B-xLingual.Q4KM.gguf1.12 GBQ4KM4-bit quantization (Medium) with K-quant
Lambda-Equulei-1.5B-xLingual.Q4KS.gguf1.07 GBQ4KS4-bit quantization (Small) with K-quant
Lambda-Equulei-1.5B-xLingual.Q5KM.gguf1.29 GBQ5KM5-bit quantization (Medium) with K-quant
Lambda-Equulei-1.5B-xLingual.Q5KS.gguf1.26 GBQ5KS5-bit quantization (Small) with K-quant
Lambda-Equulei-1.5B-xLingual.Q6_K.gguf1.46 GBQ6_K6-bit quantization with K-quant
Lambda-Equulei-1.5B-xLingual.Q8_0.gguf1.89 GBQ8_08-bit quantization

Recommended Usage

  • —Q4_K_M or Q5_K_M: Best balance of quality and performance for most users
  • —Q6_K or Q8_0: Higher quality, moderate file sizes
  • —Q2_K or Q3_K_S: Fastest inference, lower quality (good for resource-constrained environments)
  • —F16 or BF16: High quality, requires more VRAM
  • —F32: Highest quality, requires significant VRAM

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png