baseten on Hugging Face: model downloads
baseten has 262 tracked models, downloaded 35,684 times in the last 30 days and 381,151 times in total. baseten Wrapped: the last 12 months.
Models by downloads in the last 30 days
- baseten/Llama-3.2-3B-Instruct-pythonic 19.4K downloads, text generation
- baseten/DeepSeek-V3-FP4 6.5K downloads, model
- baseten/Kimi-K2-Instruct-FP4 6.3K downloads, model
- baseten/GLM-5.2-Vision-NVFP4 508 downloads, image text to text
- baseten/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4-dequant-to-BF16 114 downloads, text generation
- baseten/mixtral_i32000_o1024_bs4_tp1_A100_int8_weights_only-tllm_0.9.0.dev2024040200 98 downloads, model
- baseten/GLM-5.2-Vision-FP8 98 downloads, image text to text
- baseten/mistral_i32000_o1024_bs2_int8-weights-only_tp2_A10G_tllm_0.9.0.dev2024040200 98 downloads, model
- baseten/mistral_i32000_o1024_bs2_fp16_tp2_A10G_tllm_0.9.0.dev2024040200 97 downloads, model
- baseten/mixtral_i32000_o1024_bs4_tp1_H100_int8_weights_only-tllm_0.9.0.dev2024040200 96 downloads, model
- baseten/mixtral_i32000_o1024_bs6_A100_tp2-tllm_0.9.0.dev2024040200 95 downloads, model
- baseten/mixtral_i32000_o4096_bs4_tp2-tllm_0.9.0.dev2024022000 95 downloads, model
- baseten/mistral_i32000_o1024_bs4_int8-weights-only_tp1-A100-tllm_0.9.0.dev2024040200 93 downloads, model
- baseten/kimi-k3-tokenizer 92 downloads, model
- baseten/mixtral_i32000_o1024_bs6_H100_tp2-tllm_0.9.0.dev2024040200 91 downloads, model
- baseten/mistral_i32000_o1024_bs4_fp16_tp1-A100-tllm_0.9.0.dev2024040200 91 downloads, model
- baseten/orpheus-3b-0.1-ft-fp8 83 downloads, model
- baseten/gemma-4-26b-a4b-it-sequence-classification 75 downloads, model
- baseten/Wan2.2-T2V-A14B-LightX2V-V2.0-4step 73 downloads, text to video
- baseten/orpheus-3b-0.1-ft 40 downloads, text to speech
- baseten/example-Meta-Llama-3-70B-InstructForSequenceClassification 38 downloads, model
- baseten/k3-dspark-block8-window16384-large 30 downloads, model
- baseten/k3-dspark-block16-window512 25 downloads, model
- baseten/trtllm_mistral_fp8_i2048_o2048_bs32 25 downloads, model
- baseten/Qwen3-4B-NVFP4-PTQ 24 downloads, model
- baseten/btest-engine-builder-tllm-llama-1b 22 downloads, text generation
- baseten/gemma-4-e2b-it-sequence-classification 22 downloads, text classification
- baseten/Qwen3-1.7B-NVFP4-PTQ 21 downloads, model
- baseten/gemma-3-27b-causallm-it 17 downloads, model
- baseten/llama-3.3-70B-smoothquant-tllm 16 downloads, text generation
- baseten/Qwen2.5-Coder-32B-Instruct-128k 16 downloads, text generation
- baseten/DeepSeek-R1-0528-FP4 16 downloads, model
- baseten/deepseek-tp1-rope 14 downloads, model
- baseten/Llama-4-Scout-17B-16E-fp4 14 downloads, model
- baseten/btest-Qwen2.5-0.5B-Instruct-FP8-dynamic-NVIDIA-H100-80GB-HBM3-v0.13.0-TP1 14 downloads, model
- baseten/trtllm_llama2-7b-fp16_h100_i2048_o2048_bs128 13 downloads, model
- baseten/trtllm_llama70b_fp8_i1024_o1024_bs128_tp2 13 downloads, model
- baseten/bloom-560-tp2-default 12 downloads, model
- baseten/glm-52-debug 12 downloads, model
- baseten/DummyGemmaTextModelForEmbedding 12 downloads, feature extraction
- baseten/smol_llama-101M-GQA 12 downloads, text generation
- baseten/deepseek-v3-engine 12 downloads, model
- baseten/deepseek-v3-engine-32k 12 downloads, model
- baseten/v3-nextn-head0 12 downloads, model
- baseten/trtllm_mistral_i2048_o2048_bs128 11 downloads, model
- baseten/tinyllama_for_trtllm_specdec_draft_model_v0.12.0_tp1 11 downloads, model
- baseten/btest-Qwen2.5-0.5B-Instruct-FP8-dynamic-NVIDIA-H100-80GB-HBM3-v0.13.0-TP2 11 downloads, model
- baseten/trtllm_llama2-7b-fp8_h100_i2048_o2048_bs128 11 downloads, model
- baseten/distilled_8step_FLUX.2-dev 11 downloads, image to image
- baseten/7b-fp8-dynamic 11 downloads, model
- baseten/r1-nextn-heads 11 downloads, model
- baseten/embedding-smol_llama-101M-GQA 10 downloads, model
- baseten/trtllm_mistral_fp8_i1024_o1024_bs128 10 downloads, model
- baseten/trtllm_mistral_fp8_i2048_o2048_bs128 10 downloads, model
- baseten/trtllm_mistral_fp8_l4_i1024_o1024_bs64_0.9.0.dev2024022000 10 downloads, model
- baseten/writer_palmyra_med_70b_32K_i25000_o7000_bs16_tp4_A100_0.9.0.dev2024040200 10 downloads, model
- baseten/tinyllama_for_trtllm_specdec_target_model_v0.12.0_tp1 10 downloads, model
- baseten/btest-Mistral-7B-Instruct-v0.3-NVIDIA-H100-80GB-HBM3-v0.12.0-TP2 10 downloads, model
- baseten/dbrx-instruct_i28000_o4000_bs4_tp4_int8_weights_only-A100-tllm_0.10.0.dev2024041600 10 downloads, model
- baseten/r1-nextn-head0 9 downloads, model
- baseten/writer_llama3_70b_32K_i25000_o7000_bs16_tp4_A100_0.11.0.dev2024052100 9 downloads, model
- baseten/Llama-3.2-3B-Instruct-fp8nokv 9 downloads, model
- baseten/jo-llama-2-7b-tp4-a10g 9 downloads, model
- baseten/mistral7b-bs128-i1024-o1024-trtllm06c0e9b1-A100 9 downloads, model
- baseten/llama3-8b-i7000-o1000-with-lora-trtllm-0.11.0.dev2024052100-h100-mig-tp1-fixed-2 9 downloads, model
- baseten/RandomQwen2ForSequenceClassification-0.5B 9 downloads, text classification
- baseten/qwen3-embed-0.6b-h100 8 downloads, model
- baseten/smol_llama-101M-GQAForSequenceClassification 8 downloads, text classification
- baseten/solar_fp8_tp1_weights 8 downloads, model
- baseten/llama-3-8b-medusa-fp16 8 downloads, model
- baseten/Llama-4-Scout-17B-16E-fp8 8 downloads, model
- baseten/btest-TinyLlama-1.1B-Chat-v1.0-NVIDIA-A10G-v0.20.0-TP1 8 downloads, model
- baseten/solar_fp8_tp1_i6000_o1000_bs64-tllm_0.9.0.dev2024022000 8 downloads, model
- baseten/Qwen2.5-32B-Instruct-128k 8 downloads, text generation
- baseten/llama3-70b-instruct_fp8_tp4_i7168_o1024_bs32-tllm_0.9.0 8 downloads, model
- baseten/writer_palmyra_fin_70b_32K_i25000_o7000_bs16_tp4_A100_0.9.0.dev2024040200 8 downloads, model
- baseten/upstage-SOLAR-10.7B-v1.0_fp8_tp2_i4096_o512_bs16-tllm_0.10.0.dev2024050700 8 downloads, model
- baseten/writer_palmyra_fin_70b_32K_i25000_bs16_tp4_A100_0.12.0.dev2024080600 8 downloads, model
- baseten/mistral_fp8_tp8_i2048_o2048_bs128-tllm_0.9.0.dev2024022000 8 downloads, model
- baseten/specdec-target-mistral-7B 8 downloads, model
- baseten/vicuna-medusa_i1024_o1024_bs_fp16_tp1-tllm_0.9.0.dev2024040200 8 downloads, model
- baseten/llama-7b_fp8_tp2_i1024_o1024_bs64-tllm_0.9.0.dev2024022000 7 downloads, model
- baseten/btest-Llama-3.1-8B-Instruct-NVIDIA-H100-80GB-HBM3-v0.16.0-TP1 7 downloads, model
- baseten/llama-3-70b_fp8_tp2_i4096_o1024_bs30-tllm_0.9.0.dev2024022000 7 downloads, model
- baseten/solar-10b_fp8_tp2_i4096_o512_bs16-tllm_0.10.0.dev2024050700 7 downloads, model
- baseten/solar-SOLAR-10.7B-v1.0_i2000_o512_bs32_fp8_tp2-tllm_0.9.0.dev2024022000 7 downloads, model
- baseten/llama3-70b-fp8-fp8kv-bs64-i256-o128 7 downloads, model
- baseten/llama-70b_fp8_tp2_i1024_o100_bs32-tllm_0.12.0.dev2024072301 7 downloads, model
- baseten/btest-llama3.1-70b-instruct-NVIDIA-H100-80GB-HBM3-0.15.0-TP1-fp8-checkpoint 7 downloads, model
- baseten/Gryphe_MythoMax-L2-13b_v0.7.1_H100-80GB-HBM3_fp8 7 downloads, model
- baseten/solar_fp8_tp1_i6000_o1000_bs84-tllm_0.9.0.dev2024022000 7 downloads, model
- baseten/mixtral-8x22B_i60000_o4000_bs2_tp4_int8_weights_only_A100-tllm_0.9.0.dev2024022000 7 downloads, model
- baseten/solar-SOLAR-10.7B-v1.0_i2000_o512_bs12_fp8_tp1-tllm_0.9.0.dev2024022000-VS 7 downloads, model
- baseten/llama-70b_fp8_tp1_i1024_o100_bs16-tllm_0.13.0.dev2024081300 7 downloads, model
- baseten/btest-Llama-3.1-8B-Instruct-NVIDIA-H100-80GB-HBM3-v0.13.0-TP2 7 downloads, model
- baseten/btest-TinyLlama_v1.1-spec-dec-NVIDIA-A100-SXM4-80GB-v0.12.0-TP1 7 downloads, model
- baseten/Meta-Llama-3.1-70B-H100-2ga0125d-TP4-FP8-7168 7 downloads, model
- baseten/solar-SOLAR-10.7B-v1.0_i2000_o512_bs12_fp8_tp2-tllm_0.9.0.dev2024022000-VS 7 downloads, model
- baseten/dolphin_i8192_o1024_bs12_fp16_tp2-tllm_0.9.0.dev2024022000 7 downloads, model
- baseten/jackfram-llama68-H100-for-testing 7 downloads, model