Model Release Log

A reverse-chronological log of every model added to NeMo AutoModel. The Recipe column links to a working example YAML you can run immediately.

See the Model Coverage Overview for release summaries, and the LLM / VLM / Multimodal / Omni / Diffusion pages for the full architecture listings.

Date	Model	HF Model ID	Modality	Recipe	Try on Brev
2026-06-12	MiniMax-M3	`MiniMaxAI/MiniMax-M3`	VLM	Documentation only	🚧
2026-06-04	Nemotron-3 Ultra-550B-A55B	`nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16`	LLM	nemotron_ultra_v3_hellaswag_peft.yaml	🚧
2026-06-03	Gemma 4 12B	`google/gemma-4-12B`	LLM	gemma_4_12b_hellaswag.yaml	🚧
2026-05-27	Step-3.7-Flash	`stepfun-ai/Step-3.7-Flash`	VLM	Documentation only	🚧
2026-05-21	Wan 2.2 T2V-A14B (two-stage)	`Wan-AI/Wan2.2-T2V-A14B-Diffusers`	Diffusion	wan2_2_t2v_flow.yaml	🚧
2026-05-19	Ling 2.0	`inclusionAI/Ling-mini-2.0`	LLM	ling_mini_2_0_squad.yaml	🚧
2026-05-17	ERNIE 4.5	`baidu/ERNIE-4.5-21B-A3B-PT`	LLM	ernie4_5_21b_a3b_hellaswag.yaml	🚧
2026-05-17	MiMo-V2-Flash	`XiaomiMiMo/MiMo-V2-Flash`	LLM	mimo_v2_flash_hellaswag.yaml	🚧
2026-04-29	Mistral Medium 3.5	`mistralai/Mistral-Medium-3.5-128B`	VLM	mistral3p5_128b_medpix.yaml	🚧
2026-04-28	Hy3-preview	`tencent/Hy3-preview`	LLM	hy3_preview_deepep.yaml	🚧
2026-04-25	DeepSeek V4 Flash	`deepseek-ai/DeepSeek-V4-Flash`	LLM	deepseek_v4_flash_hellaswag.yaml	🚧
2026-04-22	Qwen3.6-27B	`Qwen/Qwen3.6-27B`	VLM	qwen3_6_27b.yaml	🚧
2026-04-16	LLaVA-OneVision-1.5 (4B / 8B)	`lmms-lab/LLaVA-OneVision-1.5-4B-Instruct`	VLM	llava_ov_1_5_4b_finetune.yaml	🚧
2026-04-16	Qwen3.6 MoE	`Qwen/Qwen3.6-35B-A3B`	VLM	qwen3_6_35b.yaml	🚧
2026-04-12	MiniMax-M2.7	`MiniMaxAI/MiniMax-M2.7`	LLM	minimax_m2.7_hellaswag_pp.yaml
2026-04-07	GLM-5.1	`zai-org/GLM-5.1`	LLM	glm_5.1_hellaswag_pp.yaml	🚧
2026-04-02	Gemma 4	`google/gemma-4-E4B-it`	VLM	gemma4_4b.yaml	🚧
2026-03-16	Mistral Small 4	`mistralai/Mistral-Small-4-119B-2603`	VLM	mistral4_medpix.yaml	🚧
2026-03-11	Nemotron Super v3	`nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16`	LLM	nemotron_super_v3_hellaswag.yaml	🚧
2026-03-11	GLM-5	`zai-org/GLM-5`	LLM	glm_5_hellaswag_pp.yaml	🚧
2026-03-03	FLUX.1-dev	`black-forest-labs/FLUX.1-dev`	Diffusion	flux_t2i_flow.yaml	🚧
2026-03-03	Wan 2.1 T2V	`Wan-AI/Wan2.1-T2V-1.3B-Diffusers`	Diffusion	wan2_1_t2v_flow.yaml	🚧
2026-03-03	HunyuanVideo 1.5	`hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v`	Diffusion	hunyuan_t2v_flow.yaml	🚧
2026-03-02	Qwen3.5 (0.8B – 9B)	`Qwen/Qwen3.5-9B`	VLM	qwen3_5_9b.yaml	🚧
2026-02-16	Qwen3.5 MoE	`Qwen/Qwen3.5-397B-A17B`	VLM	qwen3_5_moe_medpix.yaml	🚧
2026-02-13	MiniMax-M2.5	`MiniMaxAI/MiniMax-M2.5`	LLM	minimax_m2.5_hellaswag_pp.yaml	🚧
2026-02-11	GLM-4.7-Flash	`zai-org/GLM-4.7-Flash`	LLM	glm_4.7_flash_te_packed_sequence.yaml	🚧
2026-02-09	MiniMax-M2.1	`MiniMaxAI/MiniMax-M2`	LLM	minimax_m2.1_hellaswag_pp.yaml	🚧
2026-02-06	Qwen3-VL-235B	`Qwen/Qwen3-VL-235B-A22B-Instruct`	VLM	qwen3_vl_moe_235b.yaml	🚧
2026-02-06	GLM-4.7	`zai-org/GLM-4.7`	LLM	glm_4.7_te_deepep.yaml	🚧
2026-02-06	Step-3.5-Flash	`stepfun-ai/Step-3.5-Flash`	LLM	step_3.5_flash_hellaswag_pp.yaml	🚧
2026-02-05	DeepSeek-V3.2	`deepseek-ai/DeepSeek-V3.2`	LLM	deepseek_v32_hellaswag_pp.yaml	🚧
2026-02-04	Kimi-K2.5 VL	`moonshotai/Kimi-K2.5`	VLM	kimi25vl_medpix.yaml	🚧
2026-01-30	Kimi-VL	`moonshotai/Kimi-VL-A3B-Instruct`	VLM	kimi2vl_cordv2.yaml	🚧
2026-01-12	Nemotron Flash 1B	`nvidia/Nemotron-Flash-1B`	LLM	nemotron_flash_1b_squad.yaml	🚧
2026-01-12	Nemotron Parse v1.1	`nvidia/NVIDIA-Nemotron-Parse-v1.1`	VLM	nemotron_parse_v1_1.yaml
2026-01-07	Devstral-Small-2512	`mistralai/Devstral-Small-2-24B-Instruct-2512`	LLM	devstral2_small_2512_squad.yaml	🚧
2025-12-15	Nemotron-3-Nano-30B-A3B	`nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8`	LLM	nemotron_nano_v3_hellaswag.yaml	🚧
2025-12-05	Ministral 3 (3B / 8B / 14B)	`mistralai/Ministral-8B-Instruct-2410`	VLM	ministral3_8b_medpix.yaml	🚧
2025-11-24	GLM-4.5-Air	`zai-org/GLM-4.5-Air`	LLM	glm_4.5_air_te_deepep.yaml	🚧
2025-11-19	InternVL 3.5	`OpenGVLab/InternVL3_5-4B`	VLM	internvl_3_5_4b.yaml	🚧
2025-11-10	Qwen3-Omni	`Qwen/Qwen3-30B-A3B`	Omni	qwen3_omni_moe_30b_te_deepep.yaml	🚧
2025-10-24	Qwen3-Next	`Qwen/Qwen3-235B-A22B`	LLM	qwen3_next_te_deepep.yaml	🚧
2025-10-23	Qwen3-VL (4B / 8B)	`Qwen/Qwen3-VL-8B-Instruct`	VLM	qwen3_vl_4b_instruct_rdr.yaml	🚧
2025-10-05	Mixtral 8x7B	`mistralai/Mixtral-8x7B-Instruct-v0.1`	LLM	mixtral-8x7b-v0-1_squad.yaml	🚧
2025-09-29	DeepSeek-V3	`deepseek-ai/DeepSeek-V3`	LLM	deepseekv3_pretrain.yaml	🚧
2025-09-23	GPT-OSS 20B / 120B	`openai/gpt-oss-20b`	LLM	gpt_oss_20b.yaml	🚧
2025-09-08	Moonlight 16B	`moonshotai/Moonlight-16B-A3B`	LLM	moonlight_16b_te.yaml	🚧
2025-08-27	Mistral / Mistral-Nemo	`mistralai/Mistral-7B-v0.1`	LLM	mistral_7b_squad.yaml	🚧
2025-08-27	Qwen2 / Qwen2.5	`Qwen/Qwen2.5-7B`	LLM	qwen2_5_7b_squad.yaml	🚧
2025-08-27	Gemma 2 / 3	`google/gemma-2-9b-it`	LLM	gemma_2_9b_it_squad.yaml	🚧
2025-08-27	Phi 2 / 3 / 4	`microsoft/phi-4`	LLM	phi_4_squad.yaml	🚧
2025-08-27	Granite 3.x	`ibm-granite/granite-3.3-2b-instruct`	LLM	granite_3_3_2b_instruct_squad.yaml	🚧
2025-08-27	OLMo 2	`allenai/OLMo-2-0425-1B-Instruct`	LLM	olmo_2_0425_1b_instruct_squad.yaml	🚧
2025-08-27	Seed-Coder / Seed-OSS	`ByteDance-Seed/Seed-Coder-8B-Instruct`	LLM	seed_coder_8b_instruct_squad.yaml	🚧
2025-08-27	Baichuan 2	`baichuan-inc/Baichuan2-7B-Chat`	LLM	baichuan_2_7b_squad.yaml	🚧
2025-08-27	Cohere Command-R	`CohereForAI/c4ai-command-r-v01`	LLM	cohere_command_r_7b_squad.yaml	🚧
2025-08-27	StarCoder 2	`bigcode/starcoder2-3b`	LLM	starcoder_2_7b_squad.yaml	🚧
2025-08-27	Falcon 3	`tiiuae/Falcon3-7B-Instruct`	LLM	falcon3_7b_instruct_squad.yaml	🚧
2025-08-27	GLM-4 / GLM-4-MoE	`zai-org/glm-4-9b-chat-hf`	LLM	glm_4_9b_chat_hf_squad.yaml	🚧
2025-08-27	Qwen3 / Qwen3-MoE	`Qwen/Qwen3-0.6B`	LLM	qwen3_0p6b_hellaswag.yaml	🚧
2025-08-23	Gemma 3 VL	`google/gemma-3-4b-it`	VLM	gemma3_vl_4b_cord_v2.yaml	🚧
2025-08-23	Gemma 3n	`google/gemma-3n-e4b-it`	VLM	gemma3n_vl_4b_medpix.yaml	🚧
2025-08-23	Llama 3.x	`meta-llama/Llama-3.2-1B`	LLM	llama3_2_1b_squad.yaml	🚧
2025-08-23	Qwen2.5-VL	`Qwen/Qwen2.5-VL-7B-Instruct`	VLM	qwen2_5_vl_3b_rdr.yaml	🚧
2025-08-23	Phi-4-multimodal	`microsoft/Phi-4-multimodal-instruct`	Omni	phi4_mm_cv17.yaml	🚧