Hardware / Android /Android phone · 6 GB
Android · Phone
Android phone · 6 GB
for example Pixel 7a, Galaxy A54, Redmi Note 13.
Runs 55 models fully in memory, 0 more with CPU offload. 7 of those sit close enough to 3 GB that our size estimate is what decides them.
Memory one app may use
3 GB of 6 GB
the most one app may use, not the memory in the phone — estimated
Bandwidth
28 GB/s
Runs
55
01
Specifications
Memory one app may use
3 GB of 6 GB
What one app is allowed, not the whole device.
Memory bandwidth
28 GB/s
How fast it can read the model. Sets the speed of the reply.
02
What is quantisation? →What it runs
Speech models it runs53 modelsTranscription and speech models that fit in memory. Throughput figures for a transcription model come from its text decoder, so treat this as a fit answer rather than a speed one.
Niagara 19m Batch.en20M1039 tok/sFits in memoryNiagara 38m Batch.en38M312 tok/sFits in memoryParakeet TDT CTC 110m0.1B189 tok/sFits in memoryNiagara 9m Batch.en9M1968 tok/sFits in memoryNiagara 84m Batch.en84M141 tok/sFits in memoryCanary 180m Flash0.2B116 tok/sFits in memoryZipformer cr CTC Transducer XL 290M0.3B72 tok/sFits in memoryZipformer Transducer XL 290M0.3B72 tok/sFits in memoryMoonshine Streaming Small0.1B4K208 tok/sFits in memoryHubert Large Ls960 ft0.3B65 tok/sFits in memoryWav2vec2 Large 960h Lv60 Self0.3B65 tok/sFits in memoryAudio8 ASR 0.1B0.3B33K69 tok/sFits in memoryASR Conformer Largescaleasr0.5B43 tok/sFits in memoryGranite Speech 5.0 470m Turboctc0.5B42 tok/sFits in memoryGranite Speech 5.0 470m Turboctc nc0.5B42 tok/sFits in memoryNemotron 3.5 ASR Streaming 0.6b0.6B35 tok/sFits in memoryNemotron Speech Streaming en 0.6b0.6B35 tok/sFits in memoryParakeet CTC 0.6b0.6B35 tok/sFits in memoryParakeet RNNT 0.6b0.6B35 tok/sFits in memoryParakeet TDT 0.6b v20.6B35 tok/sFits in memoryParakeet TDT 0.6b v30.6B35 tok/sFits in memoryDistil Large v3.50.8B26 tok/sFits in memoryCanary 1b Flash0.8B26 tok/sFits in memoryWhisper Large v3 Turbo0.8B26 tok/sFits in memoryQwen3 ASR 0.6B0.9B23 tok/sFits in memoryMoonshine Streaming Medium0.3B4K69 tok/sFits in memoryOwsm CTC v3.1 1B1.1B19 tok/sFits in memoryOwsm CTC v3.2 ft 1B1B21 tok/sFits in memoryOwsm CTC v4 1B1B21 tok/sFits in memoryMMS 1b All1B21 tok/sFits in memoryCanary 1b1B21 tok/sFits in memoryCanary 1b v21B21 tok/sFits in memoryParakeet CTC 1.1b1.1B19 tok/sFits in memoryParakeet RNNT 1.1b1.1B19 tok/sFits in memoryParakeet TDT 1.1b1.1B19 tok/sFits in memoryARK ASR 0.6B1.3B33K16 tok/sFits in memoryLite Whisper Large v3 Acc1.4B15 tok/sFits in memoryNyra Health CrisperWhisper1.6B13 tok/sFits in memoryWhisper Large v31.5B14 tok/sFits in memoryQwen3 ASR 0.6B HF0.8B26 tok/sFits in memoryFun ASR Nano 2512 HF0.8B26 tok/sFits in memoryMOSS Transcribe Diarize0.9B23 tok/sFits in memoryCohere Transcribe 03 20262.1B10 tok/sFits in memoryQwen3 ASR 1.7B2.3B9 tok/sFits in memoryestQwen3 ASR 1.7B HF2B10 tok/sFits in memoryGLM ASR Nano 25122.3B9 tok/sFits in memoryMoonshine Streaming Tiny0B4Kno speed estimateFits in memoryGranite 4.0 1b Speech2.3B9 tok/sFits in memoryestGranite Speech 4.1 2b2.3B9 tok/sFits in memoryestGranite Speech 4.1 2b NAR2.3B9 tok/sFits in memoryestSTT 2.6b en2.6B8 tok/sFits in memoryestCanary Qwen 2.5b2.6B8 tok/sFits in memoryestMoonshine Tiny0B194no speed estimateFits in memory
Too large for this device169 modelsThe weights do not fit even with part of them offloaded to system memory. Closest calls first.
Higgs Audio v3 STT2.7B—no speed estimateToo largeGranite Speech 3.3 2b3B—no speed estimateToo largeMOSS Transcribe Preview 2B2.4B—no speed estimateToo largeLlama 3.2 3B Instruct3.2B—no speed estimateToo largeNemotron 3.5 Content Safety4.3B—no speed estimateToo largeMinistral 3 3B 25123.8B—no speed estimateToo largeARK ASR 3B4.1B—no speed estimateToo largeVoxtral Mini 3B 25074.7B—no speed estimateToo largeGemma 3 4B4.3B—no speed estimateToo largeGemma 4 E2B it5.1B—no speed estimateToo largeHojo ASR V15.2B—no speed estimateToo largeVoxtral Mini 4B Realtime 26024.4B—no speed estimateToo largeGranite 4.0 Micro3.2B—no speed estimateToo largeReka Edge7.1B—no speed estimateToo largeLlama 3.1 8B Instruct8B—no speed estimateToo largeLlama 3 8B Lunaris8B—no speed estimateToo largeHy-MT2-7B8B—no speed estimateToo largeVibeVoice ASR HF8.3B—no speed estimateToo largeQwen3 8B8.2B—no speed estimateToo largeQwen3 VL 8B Thinking8.8B—no speed estimateToo largeGemma 3n 4B7.8B—no speed estimateToo largeGranite 4.2 8B8.8B—no speed estimateToo largePhi 4 Multimodal Instruct5.6B—no speed estimateToo largeGranite Speech 3.3 8b8.6B—no speed estimateToo largeQwen3 VL 8B Instruct8.8B—no speed estimateToo largeGranite 4.1 8B8.8B—no speed estimateToo largeMinistral 3 8B 25128.9B—no speed estimateToo largeGemma 3 12B12.2B—no speed estimateToo largeRocinante 12B12.2B—no speed estimateToo largeQwen2.5 7B Instruct7.6B—no speed estimateToo largeLlama Guard 4 12B12B—no speed estimateToo largeGemma 4 E4B it8B—no speed estimateToo largeMinistral 3 14B 251213.9B—no speed estimateToo largeUI-TARS 7B8.3B—no speed estimateToo largeUnslopNemo 12B12.2B—no speed estimateToo largeGemma 4 12B it12B—no speed estimateToo largeHiggs Audio v3 8b STT v28.9B—no speed estimateToo largeQwen3.5-9B9.7B—no speed estimateToo largeReMM SLERP 13B13B—no speed estimateToo largeQwen3 14B14.8B—no speed estimateToo largeReka Flash 320.9B—no speed estimateToo largeMistral Nemo12.2B—no speed estimateToo largeCydonia 24B V4.123.6B—no speed estimateToo largeMistral Small 323.6B—no speed estimateToo largeUncensored24B—no speed estimateToo largeMistral Small 3.1 24B24B—no speed estimateToo largegpt-oss-safeguard-20b21.5B—no speed estimateToo largeMythoMax 13B13B—no speed estimateToo largeTernary Bonsai 2 27B27B—no speed estimateToo largeQwen3.8 27B27.8B—no speed estimateToo largeVoxtral Small 24B 250724.3B—no speed estimateToo largeMuse Glimmer 30B29.8B—no speed estimateToo largeQwen3 30B A3B Instruct 250730.5B—no speed estimateToo largeGemma 4 26B A4B25.8B—no speed estimateToo largeQwen3 VL 30B A3B Instruct31.1B—no speed estimateToo largeNemotron 3.5 Lightning31.6B—no speed estimateToo largeGemma 3 27B27.4B—no speed estimateToo largeGemma 4 31B31.3B—no speed estimateToo largeNex-N2.5-Mini35.1B—no speed estimateToo largeQwen3.5-35B-A3B36B—no speed estimateToo largeQwen3 VL 30B A3B Thinking31.1B—no speed estimateToo largeNemotron 3 Nano 30B A3B31.6B—no speed estimateToo largeOlmo 3 32B Think32.2B—no speed estimateToo largeQwen3 32B32.8B—no speed estimateToo largeQwen3 VL 32B Instruct33.4B—no speed estimateToo largeQwen3.6 35B A3B36B—no speed estimateToo largeMistral Small 3.2 24B24B—no speed estimateToo largeSkyfall 36B V236.9B—no speed estimateToo largePhi 414.7B—no speed estimateToo largeGemma 2 27B27.2B—no speed estimateToo largeQwen3.5-27B27.8B—no speed estimateToo largeQwen3.6 27B27.8B—no speed estimateToo largeGLM 4.7 Flash31.2B—no speed estimateToo largeHy-MT2-30B-A3B30.1B—no speed estimateToo largeQwen3 30B A3B Thinking 250730.5B—no speed estimateToo largeQwen3 Coder 30B A3B Instruct30.5B—no speed estimateToo largeLaguna XS 2.133.4B—no speed estimateToo largeQwen2.5 Coder 32B Instruct32.8B—no speed estimateToo largeNex-N2-Mini35.1B—no speed estimateToo largeLlama 3.1 70B Instruct70.6B—no speed estimateToo largeR1 Distill Llama 70B70.6B—no speed estimateToo largeQwen3 Next 80B A3B Instruct81.3B—no speed estimateToo largeHermes 3 70B Instruct70.6B—no speed estimateToo largeQwen2.5 72B Instruct72.7B—no speed estimateToo largeHunyuan A13B Instruct80.4B—no speed estimateToo largeQwen3 Next 80B A3B Thinking81.3B—no speed estimateToo largeGLM 4.6V108B—no speed estimateToo largeCommand A111B—no speed estimateToo largegpt-oss-120b120B—no speed estimateToo largeMistral Small 4119B—no speed estimateToo largeNemotron 3 Super124B—no speed estimateToo largeLlama 3.3 70B Instruct70.6B—no speed estimateToo largeHermes 4 70B70.6B—no speed estimateToo largeLlama 3.3 Euryale 70B70.6B—no speed estimateToo largeLlama 3.1 Euryale 70B v2.270.6B—no speed estimateToo largeDevstral 2 2512125B—no speed estimateToo largeGLM 4.5V108B—no speed estimateToo largeLing-2.6-flash107B—no speed estimateToo largeLlama 4 Scout109B—no speed estimateToo largeMagnum v4 72B72.7B—no speed estimateToo largeQwen2.5 VL 72B Instruct73.4B—no speed estimateToo largeLing-3.0-flash128B—no speed estimateToo largeQwen3 Coder Next79.7B—no speed estimateToo largeLaguna S 2.1118B—no speed estimateToo largeMixtral 8x22B Instruct141B—no speed estimateToo largeGLM 4.5 Air111B—no speed estimateToo largeStep 3.7 Flash201B—no speed estimateToo largeQwen3.5-122B-A10B125B—no speed estimateToo largeMistral Medium 3.5128B—no speed estimateToo largeMiniMax M2229B—no speed estimateToo largeStep 3.5 Flash199B—no speed estimateToo largeMiniMax M2.5229B—no speed estimateToo largeQwen3 235B A22B Thinking 2507235B—no speed estimateToo largeQwen3 VL 235B A22B Thinking236B—no speed estimateToo largeQwen3 VL 235B A22B Instruct236B—no speed estimateToo largeDeepSeek V4 Flash291B—no speed estimateToo largeHy3299B—no speed estimateToo largeGLM 4.5358B—no speed estimateToo largeGLM 5.3 Flash321B—no speed estimateToo largeLaguna M.1226B—no speed estimateToo largeTrinity Large Thinking399B—no speed estimateToo largeMiniMax M2.7229B—no speed estimateToo largeMiniMax M2.1229B—no speed estimateToo largeLlama 4 Maverick402B—no speed estimateToo largeQwen3 235B A22B Instruct 2507235B—no speed estimateToo largeGLM 4.6357B—no speed estimateToo largeGLM 4.7358B—no speed estimateToo largeMiniMax M3427B—no speed estimateToo largeMiniMax-01456B—no speed estimateToo largeNex-N2.5-Pro397B—no speed estimateToo largeInkling Small266B—no speed estimateToo largeJamba Large 1.7399B—no speed estimateToo largeERNIE 4.5 VL 424B A47B424B—no speed estimateToo largeHy3 preview299B—no speed estimateToo largeDeepSeek V4 Flash Vision Exp305B—no speed estimateToo largeMiniMax M1456B—no speed estimateToo largeMiMo-V2.5311B—no speed estimateToo largeQwen3 Coder 480B A35B480B—no speed estimateToo largeNex-N2-Pro397B—no speed estimateToo largeQwen3.5 397B A17B403B—no speed estimateToo largeHermes 4 405B406B—no speed estimateToo largeHermes 3 405B Instruct406B—no speed estimateToo largeGLM 5.1754B—no speed estimateToo largeDeepSeek V4.1 Flash763B—no speed estimateToo largeHy4 preview780B—no speed estimateToo largeR1 0528685B—no speed estimateToo largeDeepSeek V3685B—no speed estimateToo largeDeepSeek V3.1685B—no speed estimateToo largeGLM 5754B—no speed estimateToo largeGLM 5.2753B—no speed estimateToo largeNemotron 3 Ultra561B—no speed estimateToo largeMiMo-V2.5-Pro1T—no speed estimateToo largeKimi K2 09051T—no speed estimateToo largeKimi K2 07111T—no speed estimateToo largeLing-2.6-1T1T—no speed estimateToo largeDeepSeek V3.1 Terminus685B—no speed estimateToo largeDeepSeek V3 0324685B—no speed estimateToo largeDeepSeek V3.2685B—no speed estimateToo largeDeepSeek V3.2 Exp685B—no speed estimateToo largeRing-2.6-1T1T—no speed estimateToo largeKimi K2.7 Code1.1T—no speed estimateToo largeKimi K2.61.1T—no speed estimateToo largeKimi K2.51.1T—no speed estimateToo largeDeepSeek V4 Pro1.6T—no speed estimateToo largeInkling952B—no speed estimateToo largeKimi K2 Thinking1.1T—no speed estimateToo largeLongCat 2.01.8T—no speed estimateToo largeKimi K32.8T—no speed estimateToo largeQwen3.8 2.4T A95B2.4T—no speed estimateToo large
224 models have a verdict on this device: 55 fit in memory, 0 spill into system memory and 169 are too large. Every one of them is on this page.