Reflect GGUF models
80 GGUF models in the Reflect family, quantized by 1 uploader. Sizes run from 8.02B to 8.03B parameters. The longest trained context is 128K tokens.
About the Reflect GGUF models
Reflect is represented on ggufmodels.com by 80 GGUF models, quantized by 1 uploader on Hugging Face. The most downloaded are reflect_llm8B_om2-mstlrg-300k460k-llm33-130k-t12_SFTt1-DPOsPSDPt1_b1, reflect_llm8B_Om2SftT1-Om2G8kOm2AgIpsdpIter1T1_b1.0 and reflect_llm8B_om2-mstlrg-300k460k-llm33-130k-t12_SFTt1-DPOsPSDPt1_b2.0. Parameter counts run from 8.02B to 8.03B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Reflect model is between 4.9 to 4.9 GB, which is the quant most people start with. Most files come from RichardErkhov (80). The quants you will meet most often are Q8_0 (80), Q6_K (80), Q5_K_S (80) and Q5_K_M (80), where the number is how many models offer that quant.
Frequently asked questions
Which Reflect GGUF should I download?
The most downloaded Reflect GGUF here is reflect_llm8B_om2-mstlrg-300k460k-llm33-130k-t12_SFTt1-DPOsPSDPt1_b1. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Reflect model need?
Q4_K_M files of Reflect models on this site range from 4.9 to 4.9 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Reflect GGUF files come from?
The most common quantizers here are RichardErkhov. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.