Bunch of bad models
Sawyer Bowerman
soyrsoyr
AI & ML interests
cv, optimization
Recent Activity
updated a model about 9 hours ago
inference-optimization/Qwen3.8-Flash-Next-MEP50 updated a model about 9 hours ago
inference-optimization/GLM-5.3-Flash-MEP50 published a model about 9 hours ago
inference-optimization/Qwen3.8-Flash-Next-MEP50Organizations
Quantized across W4A16, FP8, NVFP4 using llm-compressor.
DeepSeek-MoE-16B-Chat quantized with GPTQ via llm-compressor: W8A8, W4A16, FP8, NVFP4.
-
soyrsoyr/deepseek-moe-16b-chat-W8A8-GPTQ
Text Generation • 16B • Updated • 48 -
soyrsoyr/deepseek-moe-16b-chat-W4A16-GPTQ
Text Generation • 3B • Updated • 179 -
soyrsoyr/deepseek-moe-16b-chat-FP8-GPTQ
Text Generation • 16B • Updated • 5 -
soyrsoyr/deepseek-moe-16b-chat-NVFP4-GPTQ
Text Generation • 9B • Updated • 33
tiny models for development
Bunch of good models
GPTQ quantized across W4A16, W8A8, FP8, NVFP4 using llm-compressor.
-
soyrsoyr/Llama-3.2-1B-Instruct-W4A16-GPTQ
Text Generation • 1B • Updated • 6 -
soyrsoyr/Llama-3.2-1B-Instruct-W8A8-GPTQ
Text Generation • 1B • Updated • 13 -
soyrsoyr/Llama-3.2-1B-Instruct-FP8-GPTQ
Text Generation • 1B • Updated • 9 -
soyrsoyr/Llama-3.2-1B-Instruct-NVFP4-GPTQ
Text Generation • 0.8B • Updated • 9
Bunch of bad models
Bunch of good models
Quantized across W4A16, FP8, NVFP4 using llm-compressor.
GPTQ quantized across W4A16, W8A8, FP8, NVFP4 using llm-compressor.
-
soyrsoyr/Llama-3.2-1B-Instruct-W4A16-GPTQ
Text Generation • 1B • Updated • 6 -
soyrsoyr/Llama-3.2-1B-Instruct-W8A8-GPTQ
Text Generation • 1B • Updated • 13 -
soyrsoyr/Llama-3.2-1B-Instruct-FP8-GPTQ
Text Generation • 1B • Updated • 9 -
soyrsoyr/Llama-3.2-1B-Instruct-NVFP4-GPTQ
Text Generation • 0.8B • Updated • 9
DeepSeek-MoE-16B-Chat quantized with GPTQ via llm-compressor: W8A8, W4A16, FP8, NVFP4.
-
soyrsoyr/deepseek-moe-16b-chat-W8A8-GPTQ
Text Generation • 16B • Updated • 48 -
soyrsoyr/deepseek-moe-16b-chat-W4A16-GPTQ
Text Generation • 3B • Updated • 179 -
soyrsoyr/deepseek-moe-16b-chat-FP8-GPTQ
Text Generation • 16B • Updated • 5 -
soyrsoyr/deepseek-moe-16b-chat-NVFP4-GPTQ
Text Generation • 9B • Updated • 33
tiny models for development