Top models by downloads
gemma-4-26B-A4B-it-FP8-dynamic
RRedHatAI
image text to text · transformers · Base model: google/gemma-4-26B-A4B-it
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8
RRedHatAI
text generation · transformers · Base model: nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Qwen3.6-35B-A3B-NVFP4
RRedHatAI
image text to text · transformers · Base model: Qwen/Qwen3.6-35B-A3B
gemma-4-26B-A4B-it-NVFP4
RRedHatAI
image text to text · transformers · Base model: google/gemma-4-26B-A4B-it
gemma-4-31B-it-FP8-block
RRedHatAI
image text to text · transformers · Base model: google/gemma-4-31B-it
Llama-3.2-3B-Instruct-FP8-dynamic
RRedHatAI
text generation · Base model: meta-llama/Llama-3.2-3B-Instruct · en, de, fr, it, pt, hi, es, th
Qwen3.8-27B-INT4
RRedHatAI
image text to text · transformers · Base model: Qwen/Qwen3.8-27B · en, zh
Qwen3-32B-NVFP4
RRedHatAI
text generation · Base model: Qwen/Qwen3-32B · en, de, fr, it, pt, hi, es, th
Qwen3.5-9B-FP8-dynamic
RRedHatAI
image text to text · transformers · Base model: Qwen/Qwen3.5-9B
Meta-Llama-3.1-70B-Instruct-FP8
RRedHatAI
text generation · transformers · Base model: meta-llama/Meta-Llama-3.1-70B-Instruct · en, de, fr, it, pt, hi, es, th
gemma-4-31B-it-NVFP4
RRedHatAI
image text to text · transformers · Base model: google/gemma-4-31B-it
gemma-4-31B-it-FP8-dynamic
RRedHatAI
image text to text · transformers · Base model: google/gemma-4-31B-it
Mistral-Small-24B-Instruct-2501-FP8-dynamic
RRedHatAI
text generation · Base model: mistralai/Mistral-Small-24B-Instruct-2501 · en, fr, de, es, it, pt, zh, ja, ru, ko
Qwen2.5-VL-7B-Instruct-FP8-Dynamic
RRedHatAI
image text to text · transformers · Base model: Qwen/Qwen2.5-VL-7B-Instruct · en
Qwen3.5-122B-A10B-NVFP4
RRedHatAI
Base model: Qwen/Qwen3.5-122B-A10B
Llama-3.3-70B-Instruct-FP8-dynamic
RRedHatAI
text generation · Base model: meta-llama/Llama-3.3-70B-Instruct · en, de, fr, it, pt, hi, es, th
Mistral-Small-3.2-24B-Instruct-2506-NVFP4
RRedHatAI
text generation · Base model: unsloth/Mistral-Small-3.2-24B-Instruct-2506 · en, de, fr, it, pt, hi, es, th
Qwen3.5-4B-quantized.w4a16
RRedHatAI
image text to text · transformers · Base model: Qwen/Qwen3.5-4B
gemma-3-27b-it-FP8-dynamic
RRedHatAI
image text to text · transformers · Base model: google/gemma-3-27b-it · en
Meta-Llama-3.1-8B-Instruct-FP8
RRedHatAI
text generation · transformers · Base model: meta-llama/Meta-Llama-3.1-8B-Instruct · en, de, fr, it, pt, hi, es, th
Muse-Glimmer-30B-FP8-block
RRedHatAI
image text to text · transformers · Base model: meta-models/Muse-Glimmer-30B
Qwen3-30B-A3B-Instruct-2507-quantized.w4a16
RRedHatAI
text generation · transformers · Base model: Qwen/Qwen3-30B-A3B-Instruct-2507
Qwen2.5-14B-Instruct-FP8-dynamic
RRedHatAI
Qwen3-8B-speculator.eagle3
RRedHatAI
text generation · transformers
DeepSeek-Coder-V2-Lite-Instruct-FP8
RRedHatAI
text generation · transformers
TinyLlama-1.1B-Chat-v1.0-pruned2.4
RRedHatAI
text generation · transformers · Base model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
Qwen2.5-7B-Instruct-FP8-dynamic
RRedHatAI
text generation · Base model: Qwen/Qwen2.5-7B-Instruct · zh, en, fr, es, pt, de, it, ru, ja, ko, vi, th, ar, id, tr, fa, nl, pl, cs, he, sv, fi, da, no, el, bg, uk, ur, sr, ms, zsm, nld
gemma-4-31B-it-speculator.eagle3
RRedHatAI
DeepSeek-V2.5-1210-FP8
RRedHatAI
text generation · transformers · en
Meta-Llama-3.1-8B-Instruct-quantized.w4a16
RRedHatAI
text generation · transformers · Base model: meta-llama/Llama-3.1-8B-Instruct · en, de, fr, it, pt, hi, es, th