majentik/Leanstral-TurboQuant
Text Generation • Updated • 1
Edit Models filters
Model Tree
Apps
Inference Providers
Models
258
Active filters: kv-cache-quantization
majentik/gemma-4-31B-RotorQuant-MLX-8bit
Image-Text-to-Text • 9B • Updated • 107 • 1
majentik/gemma-4-26B-A4B-RotorQuant-GGUF-Q4_K_M
Image-Text-to-Text • 25B • Updated • 720 • 4
majentik/Qwen3.6-35B-A3B-TurboQuant
Image-Text-to-Text • Updated • 12
rungalileo/llama-3.2-3B-instruct-trtllm-ckpt-wq_int4_awq-kv_int8
Text Generation • Updated • 5
rungalileo/mistral-7b-instruct-v0.3-trtllm-ckpt-wq_int4_awq-kv_int8
Text Generation • Updated • 1
rungalileo/llama-3.1-8b-instruct-trtllm-ckpt-wq_fp8-kv_fp8
Text Generation • Updated • 4
rungalileo/mistral-7b-instruct-v0.3-trtllm-ckpt-wq_fp8-kv_fp8
Text Generation • Updated • 16
rungalileo/llama-3.2-3b-instruct-trtllm-ckpt-wq_fp8-kv_fp8
Text Generation • Updated • 7
rungalileo/llama-3.2-3b-instruct-trtllm-ckpt-wq_nvfp4-kv_fp8
Text Generation • Updated • 8
rungalileo/llama-3.1-8b-instruct-trtllm-ckpt-wq_nvfp4-kv_fp8
Text Generation • Updated • 3
rungalileo/mistral-7b-instruct-v0.3-trtllm-ckpt-wq_nvfp4-kv_fp8
Text Generation • Updated • 2
rungalileo/llama-3.1-8b-instruct-trtllm-ckpt-wq_w8a8sq-kv_int8
Text Generation • Updated • 1
rungalileo/mistral-7b-instruct-v0.3-trtllm-ckpt-wq_w8a8sq-kv_int8
Text Generation • Updated • 1
majentik/gemma-4-E4B-turboquant
Image-Text-to-Text • 8B • Updated • 70 • 8
majentik/MERaLiON-3-10B-TurboQuant
Automatic Speech Recognition • Updated
majentik/MERaLiON-2-3B-TurboQuant
Automatic Speech Recognition • Updated
majentik/MERaLiON-2-10B-TurboQuant
Automatic Speech Recognition • Updated
majentik/gemma-4-E4B-rotorquant
Image-Text-to-Text • Updated • 1
majentik/MERaLiON-3-10B-RotorQuant
Automatic Speech Recognition • Updated
majentik/MERaLiON-2-10B-RotorQuant
Automatic Speech Recognition • Updated
majentik/MERaLiON-2-3B-RotorQuant
Automatic Speech Recognition • Updated
majentik/Qwen3.5-27B-TurboQuant
Text Generation • Updated
majentik/Qwen3.5-27B-RotorQuant
Text Generation • Updated • 1
majentik/Qwen3.5-27B-TurboQuant-MLX-4bit
Text Generation • 27B • Updated • 128 • 2
majentik/Qwen3.5-27B-TurboQuant-MLX-8bit
Text Generation • 27B • Updated • 62
majentik/Qwen3.5-27B-RotorQuant-MLX-4bit
Text Generation • 27B • Updated • 110
majentik/Qwen3.5-27B-RotorQuant-MLX-8bit
Text Generation • 27B • Updated • 63
majentik/Mistral-Small-4-119B-TurboQuant
Image-Text-to-Text • Updated
majentik/Mistral-Small-4-119B-RotorQuant
Image-Text-to-Text • Updated