AImodelsComparison.com 1,213 open · 210 API
Menu
Models Best of Trending Can I run it? Methodology MCP server About
1,423 models · 1,213 open weights · 210 API-only · refreshed nightly

Text generation models

Every model in the catalog — open weights you can self-host and API-only models — with licence or API price, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.

Type
All 1,423 Open weights (self-host) 1,213 API-only 210
Task
All text-generation 735 text-to-image 165 image-text-to-text 110 ASR 82 sentence-similarity 63 text-classification 50 translation 50 feature-extraction 46 image-classification 41 text-to-speech 23 token-classification 22 summarization 9 audio-classification 9 image-segmentation 9 object-detection 7 audio-text-to-text 1 any-to-any 1
Runs on
Any RTX 3060 · 12 GB RTX 4070 · 16 GB RTX 4090 · 24 GB 2 × 24 GB Mac M3 · 24 GB Mac M4 Max · 64 GB
Licence
Size
$
735 models
#ModelParamsContextCommercial use30dMin VRAM
451 transformer-1.3B-100B fla-hub · text-generation Open weights 1.4 B 2 K ✓ mit 153 K from 3.7 GB
452 Qwen3-4B-Instruct-2507-unsloth-bnb-4bit unsloth · text-generation Open weights 4.0 B 262 K ✓ apache-2.0 151 K from 5.0 GB
453 LFM2-24B-A2B-MLX-4bit lmstudio-community · text-generation Open weights 23.8 B 128 K other 151 K from 18.8 GB
454 CodeLlama-7b-hf codellama · text-generation Open weights 6.7 B 16 K ⚠ llama2 151 K from 16.3 GB
455 DeepSeek-V3-0324 deepseek-ai · text-generation Open weights Also via API 684.5 B 164 K ✓ mit 150 K from 860.6 GB
456 LFM2-24B-A2B-MLX-5bit lmstudio-community · text-generation Open weights 23.8 B 128 K other 149 K from 22.1 GB
457 Qwen2.5-Math-1.5B-Instruct Qwen · text-generation Open weights 1.5 B 4 K ✓ apache-2.0 149 K from 4.1 GB
458 LFM2-24B-A2B-MLX-8bit lmstudio-community · text-generation Open weights 23.8 B 128 K other 149 K from 31.9 GB
459 LFM2-24B-A2B-MLX-6bit lmstudio-community · text-generation Open weights 23.8 B 128 K other 149 K from 25.4 GB
460 Qwen3.8-27B-Uncensored-GGUF azukivc · text-generation Open weights 27.0 B — ✓ apache-2.0 149 K from 5.6 GB
461 Llama-2-13b-chat-hf meta-llama · text-generation · gated Open weights 13.0 B — ⚠ llama2 147 K from 31.1 GB
462 Qwen2.5-14B-Instruct-GGUF bartowski · text-generation Open weights 14.0 B 33 K ✓ apache-2.0 147 K from 8.5 GB
463 pythia-160m-deduped EleutherAI · text-generation Open weights 210 M 2 K ✓ apache-2.0 145 K from 0.9 GB
464 Qwopus3.6-27B-Fusion-GGUF KyleHessling1 · text-generation Open weights — — other 145 K from 15.4 GB
465 Granite-4.2-3B-BE-GGUF taronaeo · text-generation Open weights 3.0 B — ✓ apache-2.0 144 K from 2.6 GB
466 GLM-4.5-Air-GGUF unsloth · text-generation Open weights 110.5 B 131 K ✓ mit 144 K from 59.4 GB
467 Meta-Llama-3.1-70B-Instruct-FP8 RedHatAI · text-generation Open weights 70.6 B 131 K ⚠ llama3.1 142 K from 91.0 GB
468 DeepSeek-V4-Pro-0813 deepseek-ai · text-generation Open weights Also via API 1,650.5 B 1.0 M ✓ mit 142 K from 1,230.1 GB
469 Qwen3-Next-80B-A3B-Instruct Qwen · text-generation Open weights Also via API 81.3 B 262 K ✓ apache-2.0 141 K from 191.6 GB
470 Nanbeige_Nanbeige4.3-33B-GGUF bartowski · text-generation Open weights 33.0 B — ✓ apache-2.0 140 K from 16.5 GB
471 Qwen3-235B-A22B-Instruct-2507 Qwen · text-generation Open weights Also via API 235.1 B 262 K ✓ apache-2.0 139 K from 553.0 GB
472 DeepSeek-R1-Distill-Qwen-7B-GGUF bartowski · text-generation Open weights 7.0 B 131 K unknown 139 K from 4.6 GB
473 typhoon2.5-qwen3-4b typhoon-ai · text-generation Open weights 4.0 B 262 K ✓ apache-2.0 139 K from 10.0 GB
474 JevK5 alibiserikbay · text-generation Open weights 4.2 B 262 K ✓ apache-2.0 138 K from 10.4 GB
475 Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated-NVFP4 YuYu1015 · text-generation Open weights 30.0 B 262 K ✓ apache-2.0 138 K from 24.9 GB
476 DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-GGUF AtomicChat · text-generation Open weights 763.2 B — ✓ mit 137 K from 158.3 GB
477 MiMo-V2.5 XiaomiMiMo · text-generation Open weights Also via API 310.8 B 1.0 M ✓ mit 137 K from 394.4 GB
478 needle3 Cactus-Compute · text-generation Open weights — 8 K ✓ apache-2.0 136 K from 0.8 GB
479 DialoGPT-medium microsoft · text-generation Open weights — — ✓ mit 136 K —
480 GLM-4.7-Flash-MLX-8bit lmstudio-community · text-generation Open weights 29.9 B 203 K ✓ mit 136 K from 40.0 GB
481 Meta-Llama-3-70B meta-llama · text-generation · gated Open weights 70.6 B — ⚠ llama3 136 K from 166.3 GB
482 tiny-mpt-random-remote-code echarlaix · text-generation Open weights — — ✓ apache-2.0 135 K —
483 Hy-Memory-30B-A3B-GGUF rapatsky · text-generation Open weights 30.0 B — ✓ apache-2.0 134 K from 25.1 GB
484 GLM-5.2-FP8 zai-org · text-generation Open weights 753.3 B 1.0 M ✓ mit 132 K from 944.7 GB
485 NVIDIA-Nemotron-3.5-Bolt-E4B-4GB nvidia · text-generation Open weights 4.0 B — other 132 K from 7.9 GB
486 Qwen2.5-Coder-7B-Instruct unsloth · text-generation Open weights 7.6 B 33 K ✓ apache-2.0 132 K from 18.4 GB
487 Llama-3.2-1B-Instruct-GGUF bartowski · text-generation Open weights — — ⚠ llama3.2 132 K from 1.2 GB
488 Qwen2.5-7B-Instruct unsloth · text-generation Open weights 7.6 B 33 K ✓ apache-2.0 130 K from 18.4 GB
489 GLM-4.5 zai-org · text-generation Open weights Also via API 358.3 B 131 K ✓ mit 111 K from 842.6 GB
490 Mistral-Small-3.2-24B-Instruct-2506 mistralai · text-generation Open weights Also via API 24.0 B — ✓ apache-2.0 105 K from 109.8 GB
491 Mistral-Nemo-Instruct-2407 mistralai · text-generation Open weights Also via API 12.2 B 131 K ✓ apache-2.0 97 K from 56.2 GB
492 Ministral-3-8B-Instruct-2512 mistralai · text-generation Open weights Also via API 8.9 B — ✓ apache-2.0 94 K from 24.8 GB
493 Mistral-Small-24B-Instruct-2501 mistralai · text-generation Open weights Also via API 23.6 B 33 K ✓ apache-2.0 93 K from 107.8 GB
494 LFM3-1.7B LiquidAI · text-generation Open weights Also via API 1.7 B 262 K other 79 K from 4.6 GB
495 MiMo-V2.6-Flash-RL XiaomiMiMo · text-generation Open weights Also via API 310.8 B 1.0 M ✓ mit 77 K from 242.6 GB
496 Hy3-preview tencent · text-generation Open weights Also via API 298.8 B 262 K other 69 K from 702.7 GB
497 Hunyuan-A13B-Instruct tencent · text-generation Open weights Also via API 80.4 B 33 K other 69 K from 189.4 GB
498 Ministral-3-3B-Instruct-2512 mistralai · text-generation Open weights Also via API 3.8 B — ✓ apache-2.0 66 K from 11.4 GB
499 granite-4.2-8b ibm-granite · text-generation Open weights Also via API 8.8 B 131 K ✓ apache-2.0 60 K from 21.2 GB
500 Qwen3-Coder-480B-A35B-Instruct Qwen · text-generation Open weights Also via API 480.2 B 262 K ✓ apache-2.0 58 K from 1,128.9 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.