Robert Sinclair

Discord: https://discord.com/channels/@robert_46007

These are my own quantizations (updated almost daily).

The difference with normal quantizations is that I quantize the output and embed tensors to f16.
and the other tensors to 15_k,q6_k or q8_0.
This creates models that are little or not degraded at all and have a smaller size.
They run at about 3-6 t/sec on CPU only using llama.cpp
And obviously faster on computers with potent GPUs

ALL the models were quantized in this way:

python llama.cpp/convert_hf_to_gguf.py --outtype f16 model --outfile model.f16.gguf

quantize.exe --allow-requantize --output-tensor-type f16 --token-embedding-type f16 model.f16.gguf model.f16.q5.gguf q5_k  
quantize.exe --allow-requantize --output-tensor-type f16 --token-embedding-type f16 model.f16.gguf model.f16.q6.gguf q6_k  
quantize.exe --allow-requantize --output-tensor-type f16 --token-embedding-type f16 model.f16.gguf model.f16.q6.gguf q8_0  
quantize.exe --allow-requantize --pure model.f16.gguf model.f16.q8_p.gguf q8_0   

• ZeroWw/Phi-3.5-mini-instruct_Uncensored-GGUF
• ZeroWw/Phi-3.5-mini-instruct-GGUF
• ZeroWw/ghost-8b-beta-1608-GGUF
• ZeroWw/Llama-3.1-Storm-8B-GGUF
• ZeroWw/Llama-3.1-Minitron-4B-Width-Base-GGUF
• ZeroWw/Llama3.1-8B-Enigma-GGUF
• ZeroWw/Llama3.1-8B-ShiningValiant2-GGUF
• ZeroWw/neural-chat-7b-v3-3-GGUF
• ZeroWw/shieldgemma-2b-GGUF
• ZeroWw/Gemmasutra-Mini-2B-v1-GGUF
• ZeroWw/gemma-2-2b-it-abliterated-GGUF
• ZeroWw/gemma-2-2b-it-GGUF
• ZeroWw/gemma-2b-it-GGUF
• ZeroWw/TwinLlama-3.1-8B-GGUF
• ZeroWw/Replete-LLM-Qwen2-7b_Beta-Preview-GGUF
• ZeroWw/Celeste-12B-V1.6-GGUF
• ZeroWw/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF
• ZeroWw/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-GGUF
• ZeroWw/SOLAR-10.7B-Instruct-v1.0-GGUF
• ZeroWw/L3.1-8B-Celeste-V1.5-GGUF
• ZeroWw/Lumimaid-v0.2-8B-GGUF
• ZeroWw/Meta-Llama-3.1-8B-Instruct-GGUF
• ZeroWw/Lumimaid-v0.2-12B-GGUF
• ZeroWw/Meta-Llama-3.1-8B-Claude-39fail-3000total-GGUF
• ZeroWw/Symbol-LLM-8B-Instruct-GGUF
• ZeroWw/Meta-Llama-3-8B-Instruct-GGUF
• ZeroWw/ghost-8b-beta-GGUF
• ZeroWw/Mistral-Nemo-Base-2407-GGUF
• ZeroWw/Mistral-Nemo-Instruct-2407-GGUF
• ZeroWw/llama-3-Nephilim-v3-8B-GGUF
• ZeroWw/h2ogpt-4096-llama2-13b-chat-GGUF
• ZeroWw/L3-8B-Celeste-V1.2-GGUF
• ZeroWw/xLAM-7b-fc-r-GGUF
• ZeroWw/xLAM-1b-fc-r-GGUF
• ZeroWw/Mistral-7B-Instruct-v0.3-GGUF
• ZeroWw/L3-Nymeria-15B-GGUF
• ZeroWw/L3-8b-Rosier-v1-GGUF
• ZeroWw/llama3-turbcat-instruct-8b-GGUF
• ZeroWw/L3-SthenoMaid-8B-V1-GGUF
• ZeroWw/L3-8B-Celeste-v1-GGUF
• ZeroWw/Gemmasutra-9B-v1b-GGUF
• ZeroWw/ghost-7b-alpha-GGUF
• ZeroWw/palmer-004-turbo-GGUF
• ZeroWw/Hermes-2-Pro-Llama-3-8B-GGUF
• ZeroWw/h2o-danube3-4b-chat-GGUF
• ZeroWw/h2o-danube3-500m-chat-GGUF
• ZeroWw/Mixtral_AI_Cyber_4.0-GGUF
• ZeroWw/Llama-3-8B-Lexi-Uncensored-GGUF
• ZeroWw/open_llama_7b_v2-GGUF
• ZeroWw/open_llama_3b_v2-GGUF
• ZeroWw/Tiger-Gemma-9B-v1-GGUF
• ZeroWw/Arcee-Spark-GGUF
• ZeroWw/gpt2-xl-GGUF
• ZeroWw/glm-4-9b-chat-1m-GGUF
• ZeroWw/phillama-3.8b-v0.1-GGUF
• ZeroWw/codegeex4-all-9b-GGUF
• ZeroWw/DeepSeek-V2-Lite-Chat-GGUF
• ZeroWw/NuminaMath-7B-TIR-GGUF
• ZeroWw/Phi-3-mini-128k-instruct-abliterated-v3-GGUF
• ZeroWw/Phi-3-song-lyrics-1.0-GGUF
• ZeroWw/LLaMAX3-8B-Alpaca-GGUF
• ZeroWw/LLaMAX3-8B-GGUF
• ZeroWw/Moistral-11B-v3-GGUF
• ZeroWw/Moistral-11B-v4-GGUF
• ZeroWw/L3-Blackfall-Summanus-v0.1-15B-GGUF
• ZeroWw/Smegmma-Deluxe-9B-v1-GGUF
• ZeroWw/Smegmma-9B-v1-GGUF
• ZeroWw/internlm2_5-7b-chat-1m-GGUF
• ZeroWw/internlm2_5-7b-chat-GGUF
• ZeroWw/Phi-3-mini-4k-instruct-GGUF
• ZeroWw/glm-4-9b-chat-GGUF
• ZeroWw/llama3-8B-DarkIdol-2.2-Uncensored-1048K-GGUF
• ZeroWw/Gemma-2-9B-It-SPPO-Iter3-GGUF
• ZeroWw/Phi-3-mini-4k-geminified-GGUF
• ZeroWw/CodeQwen1.5-7B-Chat-GGUF
• ZeroWw/NeuralPipe-7B-slerp-GGUF
• ZeroWw/Llama-3-8B-Instruct-Gradient-4194k-GGUF
• ZeroWw/gemma-2-9b-it-GGUF
• ZeroWw/llama3-8B-DarkIdol-2.1-Uncensored-32K-GGUF
• ZeroWw/Meta-Llama-3-8B-Instruct-abliterated-v3-GGUF
• ZeroWw/Hathor_Stable-v0.2-L3-8B-GGUF
• ZeroWw/L3-Aethora-15B-V2-GGUF
• ZeroWw/L3-8B-Stheno-v3.3-32K-GGUF
• ZeroWw/Llama-3-8B-Instruct-Gradient-1048k-GGUF
• ZeroWw/Pythia-Chat-Base-7B-GGUF
• ZeroWw/Yi-1.5-6B-Chat-GGUF
• ZeroWw/DeepSeek-Coder-V2-Lite-Base-GGUF
• ZeroWw/Yi-1.5-9B-32K-GGUF
• ZeroWw/aya-23-8B-GGUF
• ZeroWw/MixTAO-7Bx2-MoE-v8.1-GGUF
• ZeroWw/Phi-3-medium-128k-instruct-GGUF
• ZeroWw/Phi-3-mini-128k-instruct-GGUF
• ZeroWw/Qwen1.5-7B-Chat-GGUF
• ZeroWw/NeuralDaredevil-8B-abliterated-GGUF
• ZeroWw/Mistroll-7B-v2.2-GGUF
• ZeroWw/Samantha-Qwen-2-7B-GGUF
• ZeroWw/microsoft_WizardLM-2-7B-GGUF
• ZeroWw/NSFW_DPO_Noromaid-7b-Mistral-7B-Instruct-v0.1-GGUF