Small Model Hub

3,618 efficient AI models across 9 domains · Charts · API

Domain

All (3,618)Vision (1,615)3D (743)Embedding (472)Multimodal (305)Edge/Mobile (172)Code (125)Speech (89)Video (49)NLP (48)

Task

All Tasks Speech Recognition (67)Speech (13)audio generation (6)Image Classification (2)voice activity detection (1)

Max Size≤10M ≤50M ≤100M ≤500M All

Max VRAM≤512MB ≤1GB ≤2GB ≤4GB ≤8GB All

Score

Raw Context (0-100)

Raw benchmark score — scale varies by task

Showing 89 models

#	Model	Domain	Task	Params ↑	GFLOPs	VRAM	Score	Speed	Arch	Source
1	Silero-VAD	Speech	voice activity detection	0.24M	—	1 MB	——	—	—	Qualcomm AI Hub
2	YamNet	Speech	Image Classification	3.73M	—	9 MB	——	—	—	Qualcomm AI Hub
3	abr-ai/niagara-9m-batch.en	Speech	Speech Recognition	9.00M	—	22 MB	——	7158 RTFx	State-space model/CTC	Open ASR
4	abr-ai/niagara-19m-batch.en	Speech	Speech Recognition	20.0M	—	48 MB	——	4324 RTFx	State-space model/CTC	Open ASR
5	abr-ai/niagara-38m-batch.en	Speech	Speech Recognition	38.0M	—	91 MB	——	4015 RTFx	—	Open ASR
6	DeepSpeech2	Speech	Speech	94.6M	—	227 MB	——	—	—	Qualcomm AI Hub
7	HuggingFace-WavLM-Base-Plus	Speech	Speech	95.1M	—	228 MB	——	—	—	Qualcomm AI Hub
8	nvidia/canary-180m-flash	Speech	Speech Recognition	180.0M	—	432 MB	——	2489 RTFx	Conformer-based/Transformer	Open ASR
9	FunASR-Conformer-EN	Speech	Speech	220.0M	—	528 MB	——	—	—	Qualcomm AI Hub
10	soundsgoodai/Zipformer-cr-ctc-transducer-XL-290M	Speech	Speech Recognition	290.0M	—	696 MB	——	158 RTFx	Zipformer/Pruned Stateless Transducer with k2 modified_beam_search	Open ASR
11	soundsgoodai/Zipformer-transducer-XL-290M	Speech	Speech Recognition	290.0M	—	696 MB	——	141 RTFx	Zipformer/RNN-T	Open ASR
12	AutoArk-AI/Audio8-ASR-0.1B	Speech	Speech Recognition	324.0M	—	778 MB	——	719 RTFx	Qwen3-ASR audio encoder/8-layer Qwen-style causal LM	Open ASR
13	ibm-granite/granite-speech-5.0-470m-turboctc	Speech	Speech Recognition	470.0M	—	1.1 GB	——	12946 RTFx	Streaming-style Conformer/CTC	Open ASR
14	ibm-granite/granite-speech-5.0-470m-turboctc-nc	Speech	Speech Recognition	470.0M	—	1.1 GB	——	12762 RTFx	Streaming-style Conformer/CTC	Open ASR
15	nvidia/parakeet-ctc-0.6b	Speech	Speech Recognition	600.0M	—	1.4 GB	——	5870 RTFx	Conformer-based/CTC	Open ASR
16	nvidia/parakeet-rnnt-0.6b	Speech	Speech Recognition	600.0M	—	1.4 GB	——	5431 RTFx	Conformer-based/TDT / RNN-T	Open ASR
17	nvidia/parakeet-tdt-0.6b-v2	Speech	Speech Recognition	600.0M	—	1.4 GB	——	6025 RTFx	Conformer-based/TDT / RNN-T	Open ASR
18	nvidia/parakeet-tdt-0.6b-v3	Speech	Speech Recognition	600.0M	—	1.4 GB	——	6076 RTFx	Conformer-based/TDT / RNN-T	Open ASR
19	nvidia/nemotron-speech-streaming-en-0.6b	Speech	Speech Recognition	620.0M	—	1.5 GB	——	1167 RTFx	FastConformer (cache-aware)/RNNT	Open ASR
20	nvidia/nemotron-3.5-asr-streaming-0.6b	Speech	Speech Recognition	640.0M	—	1.5 GB	——	1345 RTFx	FastConformer (cache-aware)/RNNT	Open ASR
21	Qwen/Qwen3-ASR-0.6B-hf	Speech	Speech Recognition	780.0M	—	1.8 GB	——	744 RTFx	Custom/Qwen3	Open ASR
22	distil-whisper/distil-large-v3.5	Speech	Speech Recognition	800.0M	—	1.9 GB	——	879 RTFx	Whisper/Transformer	Open ASR
23	openai/whisper-large-v3-turbo	Speech	Speech Recognition	800.0M	—	1.9 GB	——	797 RTFx	Whisper/Transformer	Open ASR
24	FunAudioLLM/Fun-ASR-Nano-2512-hf	Speech	Speech Recognition	830.0M	—	1.9 GB	——	497 RTFx	Qwen3-ASR/Custom	Open ASR
25	OpenMOSS-Team/MOSS-Transcribe-Diarize	Speech	Speech Recognition	910.0M	—	2.1 GB	——	381 RTFx	"Whisper audio encoder/24 layers"	Open ASR
26	espnet/owsm_ctc_v4_1B	Speech	Speech Recognition	1.0B	—	2.3 GB	——	777 RTFx	Whisper/CTC	Open ASR
27	nvidia/canary-1b	Speech	Speech Recognition	1.0B	—	2.3 GB	——	767 RTFx	Conformer-based/Transformer	Open ASR
28	nvidia/canary-1b-flash	Speech	Speech Recognition	1.0B	—	2.3 GB	——	2129 RTFx	Conformer-based/Transformer	Open ASR
29	nvidia/canary-1b-v2	Speech	Speech Recognition	1.0B	—	2.3 GB	——	1825 RTFx	Conformer-based/Transformer	Open ASR
30	nvidia/parakeet-ctc-1.1b	Speech	Speech Recognition	1.1B	—	2.6 GB	——	5023 RTFx	Conformer-based/CTC	Open ASR
31	nvidia/parakeet-rnnt-1.1b	Speech	Speech Recognition	1.1B	—	2.6 GB	——	4139 RTFx	Conformer-based/TDT / RNN-T	Open ASR
32	AutoArk-AI/ARK-ASR-0.6B	Speech	Speech Recognition	1.1B	—	2.7 GB	——	663 RTFx	Whisper/Qwen2	Open ASR
33	CohereLabs/cohere-transcribe-03-2026	Speech	Speech Recognition	2.0B	—	4.7 GB	——	907 RTFx	Conformer-based/Transformer	Open ASR
34	ibm-granite/granite-4.0-1b-speech	Speech	Speech Recognition	2.0B	—	4.7 GB	——	666 RTFx	Conformer-based/Granite	Open ASR
35	ibm-granite/granite-speech-4.1-2b	Speech	Speech Recognition	2.0B	—	4.7 GB	——	546 RTFx	Conformer-based/Granite	Open ASR
36	ibm-granite/granite-speech-4.1-2b-nar	Speech	Speech Recognition	2.0B	—	4.7 GB	——	2074 RTFx	Conformer-based/Hybrid CTC-LLM	Open ASR
37	openai/whisper-large-v3	Speech	Speech Recognition	2.0B	—	4.7 GB	——	470 RTFx	Whisper/Transformer	Open ASR
38	zai-org/GLM-ASR-Nano-2512	Speech	Speech Recognition	2.0B	—	4.7 GB	——	334 RTFx	Whisper/Llama	Open ASR
39	Qwen/Qwen3-ASR-1.7B-hf	Speech	Speech Recognition	2.0B	—	4.8 GB	——	820 RTFx	Custom/Qwen3	Open ASR
40	OpenMOSS-Team/MOSS-Transcribe-preview-2B	Speech	Speech Recognition	2.4B	—	5.7 GB	——	151 RTFx	Qwen3-Omni-MoE audio encoder/Qwen3	Open ASR
41	nvidia/canary-qwen-2.5b	Speech	Speech Recognition	2.5B	—	5.9 GB	——	867 RTFx	Conformer-based/Qwen2	Open ASR
42	kyutai/stt-2.6b-en	Speech	Speech Recognition	2.6B	—	6.1 GB	——	133 RTFx	Mimi tokenizer/Transformer	Open ASR
43	bosonai/higgs-audio-v3-stt	Speech	Speech Recognition	2.7B	—	6.3 GB	——	111 RTFx	Whisper/Qwen3	Open ASR
44	ibm-granite/granite-speech-3.3-2b	Speech	Speech Recognition	3.0B	—	7.0 GB	——	509 RTFx	Conformer-based/Granite	Open ASR
45	AutoArk-AI/ARK-ASR-3B	Speech	Speech Recognition	3.8B	—	8.8 GB	——	481 RTFx	Whisper/Qwen2	Open ASR
46	mistralai/Voxtral-Mini-4B-Realtime-2602	Speech	Speech Recognition	4.0B	—	9.4 GB	——	103 RTFx	Custom/Transformer	Open ASR
47	mistralai/Voxtral-Mini-3B-2507	Speech	Speech Recognition	5.0B	—	11.7 GB	——	181 RTFx	Whisper/Ministral 3B	Open ASR
48	HojoAI/Hojo-ASR-V1	Speech	Speech Recognition	5.2B	—	12.1 GB	——	73 RTFx	Qwen3-Omni encoder/Qwen3-4B	Open ASR
49	microsoft/Phi-4-multimodal-instruct	Speech	Speech Recognition	6.0B	—	14.1 GB	——	163 RTFx	Conformer-based/Phi-4-Mini-Instruct	Open ASR
50	facebook/omniASR-CTC-7B-v2	Speech	Speech Recognition	6.5B	—	15.2 GB	——	519 RTFx	Self-supervised/CTC	Open ASR
51	facebook/omniASR-LLM-7B-v2	Speech	Speech Recognition	7.8B	—	18.3 GB	——	129 RTFx	Self-supervised/Transformer	Open ASR
52	google/gemma-4-E4B-it	Speech	Speech Recognition	7.9B	—	18.6 GB	——	161 RTFx	Conformer/Transformer	Open ASR
53	microsoft/VibeVoice-ASR-HF	Speech	Speech Recognition	8.0B	—	18.8 GB	——	219 RTFx	Custom/Qwen2	Open ASR
54	bosonai/higgs-audio-v3-8b-stt-v2	Speech	Speech Recognition	8.9B	—	20.9 GB	——	137 RTFx	Whisper/Qwen3	Open ASR
55	ibm-granite/granite-speech-3.3-8b	Speech	Speech Recognition	9.0B	—	21.1 GB	——	263 RTFx	Conformer-based/Granite	Open ASR
56	mistralai/Voxtral-Small-24B-2507	Speech	Speech Recognition	24.0B	—	56.3 GB	——	101 RTFx	Whisper/Ministral 24B	Open ASR
57	Distil-Whisper	Speech	Speech	—	—	—	——	—	—	Qualcomm AI Hub
58	MeloTTS-EN	Speech	audio generation	—	—	—	——	—	—	Qualcomm AI Hub
59	MeloTTS-ES	Speech	audio generation	—	—	—	——	—	—	Qualcomm AI Hub
60	MeloTTS-ZH	Speech	audio generation	—	—	—	——	—	—	Qualcomm AI Hub
61	PiperTTS-DE	Speech	audio generation	—	—	—	——	—	—	Qualcomm AI Hub
62	PiperTTS-EN	Speech	audio generation	—	—	—	——	—	—	Qualcomm AI Hub
63	PiperTTS-IT	Speech	audio generation	—	—	—	——	—	—	Qualcomm AI Hub
64	Pyannote-Speaker-Diarization	Speech	Image Classification	—	—	—	——	—	—	Qualcomm AI Hub
65	Whisper-Base	Speech	Speech	—	—	—	——	—	—	Qualcomm AI Hub
66	Whisper-Large-V3-Turbo	Speech	Speech	—	—	—	——	—	—	Qualcomm AI Hub
67	Whisper-Large-V3-Turbo-Quantized	Speech	Speech	—	—	—	——	—	—	Qualcomm AI Hub
68	Whisper-Medium	Speech	Speech	—	—	—	——	—	—	Qualcomm AI Hub
69	Whisper-Medium-Quantized	Speech	Speech	—	—	—	——	—	—	Qualcomm AI Hub
70	Whisper-Small	Speech	Speech	—	—	—	——	—	—	Qualcomm AI Hub
71	Whisper-Small-Quantized	Speech	Speech	—	—	—	——	—	—	Qualcomm AI Hub
72	Whisper-Tiny	Speech	Speech	—	—	—	——	—	—	Qualcomm AI Hub
73	Zipformer	Speech	Speech	—	—	—	——	—	—	Qualcomm AI Hub
74	assemblyai/universal-3-5-pro	Speech	Speech Recognition	—	—	—	——	—	—	Open ASR
75	elevenlabs/scribe_v2	Speech	Speech Recognition	—	—	—	——	—	—	Open ASR
76	gladia/solaria-3	Speech	Speech Recognition	—	—	—	——	—	—	Open ASR
77	google/gemma-4-12B-it	Speech	Speech Recognition	—	—	—	——	106 RTFx	—	Open ASR
78	google/gemma-4-E2B-it	Speech	Speech Recognition	—	—	—	——	191 RTFx	Conformer/Transformer	Open ASR
79	meta/muse-voice-transcribe	Speech	Speech Recognition	—	—	—	——	—	—	Open ASR
80	microsoft/azure-speech-06-2026	Speech	Speech Recognition	—	—	—	——	—	—	Open ASR
81	microsoft/azure-speech-07-2026	Speech	Speech Recognition	—	—	—	——	—	—	Open ASR
82	modulate/multilingual	Speech	Speech Recognition	—	—	—	——	—	—	Open ASR
83	reson8/resonant-1	Speech	Speech Recognition	—	—	—	——	—	—	Open ASR
84	reson8/resonant-1-flash	Speech	Speech Recognition	—	—	—	——	—	—	Open ASR
85	smallestai/pulse	Speech	Speech Recognition	—	—	—	——	—	—	Open ASR
86	sophea/asr-k1 (preview)	Speech	Speech Recognition	—	—	—	——	—	—	Open ASR
87	speechmatics/enhanced	Speech	Speech Recognition	—	—	—	——	—	—	Open ASR
88	zoom/scribe_v1	Speech	Speech Recognition	—	—	—	——	—	—	Open ASR
89	zoom/scribe_v2_pro	Speech	Speech Recognition	—	—	—	——	—	—	Open ASR