MMLForge Search models, datasets, tasks… Start free

Home › Models › Text Generation

Best Text Generation Models

872

872 text generation models on MLForge, ranked by downloads — including work from Qwen, openai-community, facebook, trl-internal-testing. Compare, download and run them locally on your own GPU. Free tier.

Start free Desktop app

Top Text Generation models

Q Qwen/Qwen3-0.6B Text Generation ·751.6M params 27.8M 1.4K 🤗 HF G openai-community/gpt2 Text Generation ·137.0M params 13.3M 3.3K 🤗 HF Q Qwen/Qwen3-8B Text Generation ·8.2B params 13.0M 1.2K 🤗 HF Q Qwen/Qwen2.5-7B-Instruct Text Generation ·7.6B params 12.8M 1.4K 🤗 HF O facebook/opt-125m Text Generation 12.3M 267 🤗 HF Q Qwen/Qwen2.5-1.5B-Instruct Text Generation ·1.5B params 11.3M 748 🤗 HF Q Qwen/Qwen2.5-3B-Instruct Text Generation ·3.1B params 9.1M 510 🤗 HF T trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 Text Generation ·2.4M params 8.4M 7 🤗 HF D deepseek-ai/DeepSeek-R1 Text Generation ·684.5B params 7.1M 13.4K 🤗 HF G openai/gpt-oss-20b Text Generation ·21.5B params 7.0M 4.7K 🤗 HF Q Qwen/Qwen3-4B Text Generation ·4.0B params 6.0M 656 🤗 HF D antirez/deepseek-v4-gguf Text Generation 5.7M 271 🤗 HF Q Qwen/Qwen3-1.7B Text Generation ·2.0B params 5.6M 487 🤗 HF Q Qwen/Qwen3-4B-Instruct-2507 Text Generation ·4.0B params 5.6M 882 🤗 HF D deepseek-ai/DeepSeek-R1-0528 Text Generation ·684.5B params 5.5M 2.5K 🤗 HF Q Qwen/Qwen2.5-0.5B-Instruct Text Generation ·494.0M params 4.8M 541 🤗 HF Q Qwen/Qwen2.5-Coder-14B-Instruct Text Generation ·14.8B params 4.7M 166 🤗 HF D dphn/dolphin-2.9.1-yi-1.5-34b Text Generation ·34.4B params 4.7M 65 🤗 HF Q nvidia/Qwen3.6-35B-A3B-NVFP4 Text Generation ·18.7B params 4.6M 321 🤗 HF T hmellor/tiny-random-LlamaForCausalLM Text Generation ·1.1M params 4.5M 🤗 HF Q Qwen/Qwen3-32B Text Generation ·32.8B params 4.1M 708 🤗 HF D distilbert/distilgpt2 Text Generation ·88.2M params 4.1M 630 🤗 HF G openai/gpt-oss-120b Text Generation ·120.4B params 4.1M 4.9K 🤗 HF Q Qwen/Qwen2-1.5B-Instruct Text Generation ·1.5B params 3.8M 162 🤗 HF G Andycurrent/Gemma-3-1B-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking_GGUF Text Generation 3.7M 79 🤗 HF Q Qwen/Qwen2.5-7B-Instruct-AWQ Text Generation ·7.6B params 3.5M 47 🤗 HF Q Qwen/Qwen3-14B Text Generation ·14.8B params 3.0M 416 🤗 HF P EleutherAI/pythia-160m Text Generation ·212.7M params 3.0M 42 🤗 HF D deepseek-ai/DeepSeek-V3.2 Text Generation ·685.4B params 2.9M 1.4K 🤗 HF Q Qwen/Qwen3-30B-A3B Text Generation ·30.5B params 2.5M 903 🤗 HF Q Qwen/Qwen2.5-32B-Instruct Text Generation ·32.8B params 2.5M 352 🤗 HF M MiniMaxAI/MiniMax-M2.7 Text Generation ·228.7B params 2.4M 1.2K 🤗 HF Q Qwen/Qwen2.5-0.5B Text Generation ·494.0M params 2.4M 424 🤗 HF G zai-org/GLM-5-FP8 Text Generation ·753.9B params 2.3M 181 🤗 HF T TinyLlama/TinyLlama-1.1B-Chat-v1.0 Text Generation ·1.1B params 2.2M 1.6K 🤗 HF Q Qwen/Qwen2.5-14B-Instruct Text Generation ·14.8B params 2.2M 351 🤗 HF D deepseek-ai/DeepSeek-V4-Flash Text Generation ·158.1B params 2.1M 1.6K 🤗 HF S HuggingFaceTB/SmolLM2-135M-Instruct Text Generation ·134.5M params 2.1M 360 🤗 HF G zai-org/GLM-4.7-Flash Text Generation ·31.2B params 2.1M 1.8K 🤗 HF Q Qwen/Qwen3-0.6B-FP8 Text Generation ·751.7M params 2.1M 62 🤗 HF Q Qwen/Qwen3-Coder-30B-A3B-Instruct Text Generation ·30.5B params 2.0M 1.1K 🤗 HF Q Qwen/Qwen2.5-Coder-7B-Instruct Text Generation ·7.6B params 2.0M 741 🤗 HF G nvidia/Gemma-4-26B-A4B-NVFP4 Text Generation ·14.4B params 2.0M 97 🤗 HF G openai-community/gpt2-large Text Generation ·811.8M params 2.0M 353 🤗 HF P EleutherAI/pythia-70m-deduped Text Generation ·95.6M params 1.9M 28 🤗 HF L RedHatAI/Llama-3.2-1B-Instruct-FP8-dynamic Text Generation ·1.5B params 1.9M 4 🤗 HF D deepseek-ai/DeepSeek-V4-Pro Text Generation ·861.6B params 1.9M 5.1K 🤗 HF N nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 Text Generation ·4.0B params 1.8M 95 🤗 HF R prefeitura-rio/Rio-3.0-Open-Mini Text Generation ·4.0B params 1.8M 9 🤗 HF Q Qwen/Qwen3-Coder-Next-FP8 Text Generation ·79.7B params 1.7M 154 🤗 HF Q Qwen/Qwen3-14B-AWQ Text Generation ·14.8B params 1.7M 69 🤗 HF Q Qwen/Qwen2.5-Coder-32B-Instruct Text Generation ·32.8B params 1.6M 2.1K 🤗 HF K moonshotai/Kimi-K2-Instruct-0905 Text Generation ·1026.5B params 1.6M 746 🤗 HF O apple/OpenELM-1_1B-Instruct Text Generation ·1.1B params 1.6M 76 🤗 HF Q Qwen/Qwen2.5-Coder-32B-Instruct-AWQ Text Generation ·32.8B params 1.6M 37 🤗 HF P ibm-research/PowerMoE-3b Text Generation ·3.4B params 1.6M 21 🤗 HF Q Qwen/Qwen2.5-1.5B Text Generation ·1.5B params 1.5M 189 🤗 HF S HuggingFaceTB/SmolLM2-135M Text Generation ·134.5M params 1.4M 209 🤗 HF Q QuantTrio/Qwen3-VL-30B-A3B-Instruct-AWQ Text Generation ·31.1B params 1.4M 43 🤗 HF Q empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF Text Generation 1.4M 1.3K 🤗 HF Q Qwen/Qwen2.5-14B-Instruct-AWQ Text Generation ·14.8B params 1.4M 37 🤗 HF D deepseek-ai/DeepSeek-R1-0528-Qwen3-8B Text Generation ·8.2B params 1.3M 1.1K 🤗 HF G nvidia/Gemma-4-31B-IT-NVFP4 Text Generation ·20.9B params 1.3M 516 🤗 HF K nvidia/Kimi-K2.5-NVFP4 Text Generation 1.3M 86 🤗 HF N nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 Text Generation ·67.2B params 1.3M 363 🤗 HF Q Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 Text Generation ·30.5B params 1.2M 185 🤗 HF Q Qwen/Qwen3-Coder-Next Text Generation ·79.7B params 1.2M 1.5K 🤗 HF N nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 Text Generation ·123.6B params 1.2M 392 🤗 HF D deepseek-ai/DeepSeek-V3-0324 Text Generation ·684.5B params 1.2M 3.1K 🤗 HF P microsoft/Phi-3.5-mini-instruct Text Generation ·3.8B params 1.2M 993 🤗 HF Q Qwen/Qwen2.5-Coder-14B-Instruct-AWQ Text Generation ·14.8B params 1.2M 21 🤗 HF D deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct Text Generation ·15.7B params 1.1M 615 🤗 HF G zai-org/GLM-5.2-FP8 Text Generation ·753.4B params 1.1M 186 🤗 HF H h2oai/h2ovl-mississippi-800m Text Generation ·826.3M params 1.1M 40 🤗 HF Q Qwen/Qwen2.5-72B-Instruct-AWQ Text Generation ·73.0B params 1.1M 78 🤗 HF D deepseek-ai/DeepSeek-V3 Text Generation ·684.5B params 1.1M 4.1K 🤗 HF H h2oai/h2ovl-mississippi-2b Text Generation ·2.2B params 1.1M 42 🤗 HF S nm-testing/SmolLM-1.7B-Instruct-quantized.w4a16 Text Generation ·1.8B params 1.1M 🤗 HF D nvidia/diffusiongemma-26B-A4B-it-NVFP4 Text Generation ·14.4B params 1.1M 88 🤗 HF Q Qwen/Qwen2-0.5B Text Generation ·494.0M params 1.1M 169 🤗 HF D deepseek-ai/DeepSeek-V2-Lite-Chat Text Generation ·15.7B params 1.1M 141 🤗 HF G zai-org/GLM-5.1-FP8 Text Generation ·753.9B params 1.1M 119 🤗 HF N nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 Text Generation ·31.6B params 1.1M 780 🤗 HF T TheBloke/TinyLlama-1.1B-Chat-v0.3-GPTQ Text Generation ·1.1B params 1.0M 10 🤗 HF Q RedHatAI/Qwen2.5-1.5B-quantized.w8a8 Text Generation ·1.8B params 1.0M 4 🤗 HF M mistralai/Mistral-7B-Instruct-v0.2 Text Generation ·7.2B params 1.0M 3.2K 🤗 HF D nvidia/DeepSeek-R1-0528-NVFP4-v2 Text Generation ·393.6B params 1.0M 23 🤗 HF B KomeijiForce/bart-large-emojilm Text Generation 930.8K 🤗 HF N nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 Text Generation ·18.2B params 908.3K 163 🤗 HF Q Qwen/Qwen3-0.6B-Base Text Generation ·596.0M params 900.1K 174 🤗 HF M mistralai/Mistral-7B-v0.1 Text Generation ·7.2B params 885.5K 4.1K 🤗 HF L RedHatAI/Llama-3.2-1B-Instruct-FP8 Text Generation ·1.5B params 881.5K 4 🤗 HF Q Qwen/Qwen2.5-1.5B-Instruct-AWQ Text Generation ·1.8B params 880.7K 7 🤗 HF Q Qwen/Qwen3-4B-Instruct-2507-FP8 Text Generation ·4.4B params 873.2K 78 🤗 HF N nvidia/NVIDIA-Nemotron-Nano-9B-v2 Text Generation ·8.9B params 860.5K 498 🤗 HF P microsoft/phi-4 Text Generation ·14.7B params 846.7K 2.3K 🤗 HF P microsoft/Phi-tiny-MoE-instruct Text Generation ·3.8B params 831.7K 38 🤗 HF Q Qwen/Qwen3-235B-A22B Text Generation ·235.1B params 804.3K 1.1K 🤗 HF M state-spaces/mamba-130m-hf Text Generation ·129.1M params 788.4K 73 🤗 HF D deepseek-ai/DeepSeek-R1-Distill-Qwen-32B Text Generation ·32.8B params 782.2K 1.6K 🤗 HF Q Qwen/Qwen2.5-Coder-1.5B-Instruct Text Generation ·1.5B params 776.9K 132 🤗 HF P microsoft/phi-2 Text Generation ·2.8B params 769.1K 3.5K 🤗 HF Q Qwen/Qwen2.5-32B-Instruct-AWQ Text Generation ·32.8B params 759.9K 101 🤗 HF T trl-internal-testing/tiny-GptOssForCausalLM Text Generation ·3.2M params 740.4K 4 🤗 HF K nvidia/Kimi-K2.6-NVFP4 Text Generation 716.2K 39 🤗 HF Q Qwen/Qwen3-30B-A3B-Instruct-2507 Text Generation ·30.5B params 713.2K 818 🤗 HF Q Qwen/Qwen3-1.7B-Base Text Generation ·1.7B params 710.0K 75 🤗 HF S HuggingFaceTB/SmolLM3-3B Text Generation ·3.1B params 688.6K 981 🤗 HF Q Qwen/Qwen2-7B-Instruct Text Generation ·7.6B params 688.4K 686 🤗 HF M MiniMaxAI/MiniMax-M2.5 Text Generation ·228.7B params 674.7K 1.5K 🤗 HF T llamafactory/tiny-random-Llama-3 Text Generation ·4.1M params 660.6K 3 🤗 HF Q Qwen/Qwen3-4B-Base Text Generation ·4.0B params 646.7K 95 🤗 HF Q Qwen/Qwen2.5-72B-Instruct Text Generation ·72.7B params 635.2K 960 🤗 HF G yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF Text Generation 628.2K 2.6K 🤗 HF H cyankiwi/Hermes-4-14B-AWQ-4bit Text Generation ·3.6B params 620.5K 4 🤗 HF D deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B Text Generation ·1.8B params 618.6K 1.5K 🤗 HF B speakleash/Bielik-11B-v3.0-Instruct-awq Text Generation ·11.3B params 614.2K 2 🤗 HF T hmellor/tiny-random-Gemma2ForCausalLM Text Generation ·8.4M params 612.1K 🤗 HF G cyankiwi/GLM-4.5-Air-AWQ-4bit Text Generation ·18.6B params 609.9K 29 🤗 HF Q Qwen/Qwen3-8B-FP8 Text Generation ·8.2B params 609.6K 62 🤗 HF

Showing the top 120 of 872 by downloads. Browse all in MLForge →

Other tasks