Hardware / NVIDIA /GeForce RTX 5090

NVIDIA · GPU

GeForce RTX 5090

Runs 134 models fully in memory, 0 more with CPU offload.

Memory

32 GB

Bandwidth

1792 GB/s

Runs

134

01

Specifications

Memory

32 GB

Decides which models fit at all.

Memory bandwidth

1792 GB/s

How fast it can read the model. Sets the speed of the reply.

Compute

104.8 TFLOPS

Trillions of half-precision sums a second. Sets how fast it reads a long prompt, not how fast it replies.

Power draw

575 W

At full load, for sizing a power supply.

MSRP

$1,999

What the maker asked for it new. We hold no used or street prices, so this is not what one costs today.

Released

Jan 30, 2025

Architecture

Blackwell

02

What it runs

Best quant per model. Text models first, then speech, then what does not fit.

What is quantisation? →

ModelParamsContextSpeedVerdict

Granite 4.1 8B8.8B131K229 tok/sFits in memory Qwen3.6 35B A3B36B66K670 tok/sFits in memory Qwen3.5-9B9.7B131K208 tok/sFits in memory Nemotron 3 Nano 30B A3B31.6B131K670 tok/sFits in memory Ministral 3 14B 251213.9B66K170 tok/sFits in memory Ministral 3 8B 25128.9B131K152 tok/sFits in memory Ministral 3 3B 25123.8B131K622 tok/sFits in memory gpt-oss-safeguard-20b21.5B131K558 tok/sFits in memory Granite 4.0 Micro3.2B66K422 tok/sFits in memory Qwen3 VL 8B Thinking8.8B131K269 tok/sFits in memory Qwen3 VL 30B A3B Thinking31.1B66K670 tok/sFits in memory UI-TARS 7B8.3B66K163 tok/sFits in memory Llama Guard 4 12B12B262K197 tok/sFits in memory Qwen3 14B14.8B66K160 tok/sFits in memory Gemma 3 12B12.2B131K165 tok/sFits in memory Rocinante 12B12.2B66K194 tok/sFits in memory Llama 3.2 3B Instruct3.2B131K739 tok/sFits in memory Mistral Nemo12.2B131K194 tok/sFits in memory Qwen3.5-35B-A3B36B66K670 tok/sFits in memory Qwen3 VL 8B Instruct8.8B131K229 tok/sFits in memory Qwen3 VL 30B A3B Instruct31.1B66K670 tok/sFits in memory Qwen3 30B A3B Thinking 250730.5B66K670 tok/sFits in memory Qwen3 Coder 30B A3B Instruct30.5B66K670 tok/sFits in memory Qwen3 30B A3B Instruct 250730.5B66K670 tok/sFits in memory Qwen3 8B8.2B131K288 tok/sFits in memory Gemma 3 4B4.3B131K469 tok/sFits in memory Llama 3.1 8B Instruct8B131K252 tok/sFits in memory Granite 4.2 8B8.8B66K153 tok/sFits in memory Nemotron 3.5 Content Safety4.3B131K469 tok/sFits in memory Reka Flash 320.9B66K113 tok/sFits in memory Gemma 4 26B A4B25.8B33K503 tok/sFits in memory Gemma 3n 4B7.8B33K258 tok/sFits in memory UnslopNemo 12B12.2B33K194 tok/sFits in memory Llama 3.2 1B Instruct1.2B33K1971 tok/sFits in memory Qwen2.5 7B Instruct7.6B33K311 tok/sFits in memory Cydonia 24B V4.123.6B66K100 tok/sFits in memory Uncensored24B66K99 tok/sFits in memory Mistral Small 3.2 24B24B66K99 tok/sFits in memory Mistral Small 3.1 24B24B66K99 tok/sFits in memory Reka Edge7.1B16K190 tok/sFits in memory Phi 414.7B16K161 tok/sFits in memory Gemma 3 27B27.4B66K86 tok/sFits in memory Mistral Small 323.6B33K100 tok/sFits in memory Ternary Bonsai 2 27B27B66K88 tok/sFits in memory Llama 3 8B Lunaris8B8K252 tok/sFits in memory MythoMax 13B13B8K155 tok/sFits in memory Hy-MT2-1.8B2B8K1005 tok/sFits in memory Hy-MT2-30B-A3B30.1B8K571 tok/sFits in memory Hy-MT2-7B8B8K214 tok/sFits in memory Muse Glimmer 30B29.8B131K79 tok/sFits in memory Qwen3.5-27B27.8B33K85 tok/sFits in memory Voxtral Small 24B 250724.3B16K97 tok/sFits in memory ReMM SLERP 13B13B4K155 tok/sFits in memory Qwen3.6 27B27.8B33K85 tok/sFits in memory Qwen3.8 27B27.8B33K85 tok/sFits in memory Nemotron 3.5 Lightning31.6B131K64 tok/sFits in memory Olmo 3 32B Think32.2B33K73 tok/sFits in memory Nex-N2-Mini35.1B66K57 tok/sFits in memory Nex-N2.5-Mini35.1B66K57 tok/sFits in memory Gemma 2 27B27.2B8K87 tok/sFits in memory Qwen3 VL 32B Instruct33.4B16K71 tok/sFits in memory Qwen2.5 Coder 32B Instruct32.8B16K72 tok/sFits in memory Laguna XS 2.133.4B33K60 tok/sFits in memory Qwen3 32B32.8B16K72 tok/sFits in memory Gemma 4 31B31.3B8K76 tok/sFits in memory GLM 4.7 Flash31.2B16K64 tok/sFits in memory Skyfall 36B V236.9B16K64 tok/sFits in memory

Speech models it runs67 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.en20M118235 tok/sFits in memory Niagara 38m Batch.en38M35507 tok/sFits in memory Higgs Audio v3 8b STT v28.9B266 tok/sFits in memory Higgs Audio v3 STT2.7B500 tok/sFits in memory Cohere Transcribe 03 20262.1B643 tok/sFits in memory Distil Large v3.50.8B1687 tok/sFits in memory Lite Whisper Large v3 Acc1.4B1440 tok/sFits in memory Owsm CTC v3.1 1B1.1B2150 tok/sFits in memory Owsm CTC v3.2 ft 1B1B1349 tok/sFits in memory Owsm CTC v4 1B1B2365 tok/sFits in memory Hubert Large Ls960 ft0.3B4217 tok/sFits in memory MMS 1b All1B2016 tok/sFits in memory Wav2vec2 Large 960h Lv60 Self0.3B4217 tok/sFits in memory Hojo ASR V15.2B389 tok/sFits in memory Granite 4.0 1b Speech2.3B587 tok/sFits in memory Granite Speech 3.3 2b3B788 tok/sFits in memory Granite Speech 3.3 8b8.6B275 tok/sFits in memory Granite Speech 4.1 2b2.3B1028 tok/sFits in memory Granite Speech 4.1 2b NAR2.3B1028 tok/sFits in memory STT 2.6b en2.6B910 tok/sFits in memory Phi 4 Multimodal Instruct5.6B131K422 tok/sFits in memory VibeVoice ASR HF8.3B163 tok/sFits in memory Voxtral Mini 3B 25074.7B287 tok/sFits in memory Voxtral Mini 4B Realtime 26024.4B307 tok/sFits in memory Canary 180m Flash0.2B11198 tok/sFits in memory Canary 1b1B1349 tok/sFits in memory Canary 1b Flash0.8B1687 tok/sFits in memory Canary 1b v21B1349 tok/sFits in memory Canary Qwen 2.5b2.6B519 tok/sFits in memory Nemotron 3.5 ASR Streaming 0.6b0.6B2249 tok/sFits in memory Nemotron Speech Streaming en 0.6b0.6B2249 tok/sFits in memory Parakeet CTC 0.6b0.6B3941 tok/sFits in memory Parakeet CTC 1.1b1.1B1227 tok/sFits in memory Parakeet RNNT 0.6b0.6B2249 tok/sFits in memory Parakeet RNNT 1.1b1.1B2150 tok/sFits in memory Parakeet TDT CTC 110m0.1B12266 tok/sFits in memory Parakeet TDT 0.6b v20.6B3359 tok/sFits in memory Parakeet TDT 0.6b v30.6B2249 tok/sFits in memory Parakeet TDT 1.1b1.1B1227 tok/sFits in memory Nyra Health CrisperWhisper1.6B843 tok/sFits in memory Whisper Large v31.5B1344 tok/sFits in memory Whisper Large v3 Turbo0.8B2956 tok/sFits in memory MOSS Transcribe Diarize0.9B1499 tok/sFits in memory Qwen3 ASR 0.6B0.9B2627 tok/sFits in memory Qwen3 ASR 0.6B HF0.8B2956 tok/sFits in memory Qwen3 ASR 1.7B2.3B876 tok/sFits in memory Qwen3 ASR 1.7B HF2B675 tok/sFits in memory Zipformer cr CTC Transducer XL 290M0.3B6950 tok/sFits in memory Zipformer Transducer XL 290M0.3B4653 tok/sFits in memory ASR Conformer Largescaleasr0.5B4927 tok/sFits in memory GLM ASR Nano 25122.3B876 tok/sFits in memory Granite Speech 5.0 470m Turboctc0.5B4031 tok/sFits in memory Granite Speech 5.0 470m Turboctc nc0.5B4729 tok/sFits in memory Fun ASR Nano 2512 HF0.8B2956 tok/sFits in memory Gemma 4 E2B it5.1B395 tok/sFits in memory Gemma 4 E4B it8B131K169 tok/sFits in memory Niagara 9m Batch.en9M149919 tok/sFits in memory Niagara 84m Batch.en84M28151 tok/sFits in memory ARK ASR 0.6B1.3B33K1551 tok/sFits in memory ARK ASR 3B4.1B33K577 tok/sFits in memory Audio8 ASR 0.1B0.3B33K4498 tok/sFits in memory MOSS Transcribe Preview 2B2.4B33K985 tok/sFits in memory Gemma 4 12B it12B168 tok/sFits in memory Moonshine Streaming Medium0.3B4K7882 tok/sFits in memory Moonshine Streaming Small0.1B4K13493 tok/sFits in memory Moonshine Streaming Tiny0B4Kno speed estimateFits in memory Moonshine Tiny0B194no speed estimateFits in memory

Too large for this device90 modelsThe weights do not fit even with part of them offloaded to system memory. Closest calls first.

Llama 3.1 70B Instruct70.6B—no speed estimateToo largeest Llama 3.3 Euryale 70B70.6B—no speed estimateToo largeest R1 Distill Llama 70B70.6B—no speed estimateToo largeest Qwen2.5 VL 72B Instruct73.4B—no speed estimateToo largeest Qwen3 Next 80B A3B Instruct81.3B—no speed estimateToo large Llama 3.3 70B Instruct70.6B—no speed estimateToo large Qwen2.5 72B Instruct72.7B—no speed estimateToo large GLM 4.6V108B—no speed estimateToo large Command A111B—no speed estimateToo large gpt-oss-120b120B—no speed estimateToo large Hermes 4 70B70.6B—no speed estimateToo large Llama 3.1 Euryale 70B v2.270.6B—no speed estimateToo large Hermes 3 70B Instruct70.6B—no speed estimateToo large Ling-2.6-flash107B—no speed estimateToo large Llama 4 Scout109B—no speed estimateToo large Magnum v4 72B72.7B—no speed estimateToo large Qwen3 Coder Next79.7B—no speed estimateToo large Laguna S 2.1118B—no speed estimateToo large Hunyuan A13B Instruct80.4B—no speed estimateToo large Qwen3 Next 80B A3B Thinking81.3B—no speed estimateToo large Nemotron 3 Super124B—no speed estimateToo large Qwen3.5-122B-A10B125B—no speed estimateToo large Mistral Medium 3.5128B—no speed estimateToo large Mixtral 8x22B Instruct141B—no speed estimateToo large GLM 4.5V108B—no speed estimateToo large GLM 4.5 Air111B—no speed estimateToo large Step 3.7 Flash201B—no speed estimateToo large Mistral Small 4119B—no speed estimateToo large Devstral 2 2512125B—no speed estimateToo large Ling-3.0-flash128B—no speed estimateToo large MiniMax M2229B—no speed estimateToo large Step 3.5 Flash199B—no speed estimateToo large Qwen3 235B A22B Thinking 2507235B—no speed estimateToo large MiniMax M2.5229B—no speed estimateToo large DeepSeek V4 Flash291B—no speed estimateToo large GLM 5.3 Flash321B—no speed estimateToo large Hy3299B—no speed estimateToo large Laguna M.1226B—no speed estimateToo large Nex-N2-Pro397B—no speed estimateToo large Nex-N2.5-Pro397B—no speed estimateToo large Trinity Large Thinking399B—no speed estimateToo large MiniMax M2.7229B—no speed estimateToo large MiniMax M2.1229B—no speed estimateToo large Llama 4 Maverick402B—no speed estimateToo large Qwen3 235B A22B Instruct 2507235B—no speed estimateToo large Qwen3 VL 235B A22B Thinking236B—no speed estimateToo large Qwen3 VL 235B A22B Instruct236B—no speed estimateToo large GLM 4.6357B—no speed estimateToo large GLM 4.7358B—no speed estimateToo large ERNIE 4.5 VL 424B A47B424B—no speed estimateToo large MiniMax M3427B—no speed estimateToo large Inkling Small266B—no speed estimateToo large Jamba Large 1.7399B—no speed estimateToo large Hy3 preview299B—no speed estimateToo large DeepSeek V4 Flash Vision Exp305B—no speed estimateToo large MiniMax M1456B—no speed estimateToo large MiMo-V2.5311B—no speed estimateToo large Qwen3 Coder 480B A35B480B—no speed estimateToo large GLM 4.5358B—no speed estimateToo large DeepSeek V3.1685B—no speed estimateToo large Qwen3.5 397B A17B403B—no speed estimateToo large Hermes 4 405B406B—no speed estimateToo large Hermes 3 405B Instruct406B—no speed estimateToo large GLM 5.1754B—no speed estimateToo large MiniMax-01456B—no speed estimateToo large DeepSeek V3685B—no speed estimateToo large DeepSeek V3.2685B—no speed estimateToo large DeepSeek V3.2 Exp685B—no speed estimateToo large GLM 5754B—no speed estimateToo large DeepSeek V4.1 Flash763B—no speed estimateToo large GLM 5.2753B—no speed estimateToo large Nemotron 3 Ultra561B—no speed estimateToo large Ling-2.6-1T1T—no speed estimateToo large R1 0528685B—no speed estimateToo large DeepSeek V3.1 Terminus685B—no speed estimateToo large DeepSeek V3 0324685B—no speed estimateToo large Kimi K2 07111T—no speed estimateToo large Ring-2.6-1T1T—no speed estimateToo large Kimi K2.7 Code1.1T—no speed estimateToo large Kimi K2.61.1T—no speed estimateToo large Kimi K2.51.1T—no speed estimateToo large Hy4 preview780B—no speed estimateToo large DeepSeek V4 Pro1.6T—no speed estimateToo large Inkling952B—no speed estimateToo large MiMo-V2.5-Pro1T—no speed estimateToo large Kimi K2 09051T—no speed estimateToo large Kimi K2 Thinking1.1T—no speed estimateToo large LongCat 2.01.8T—no speed estimateToo large Qwen3.8 2.4T A95B2.4T—no speed estimateToo large Kimi K32.8T—no speed estimateToo large

224 models have a verdict on this device: 134 fit in memory, 0 spill into system memory and 90 are too large. Every one of them is on this page.

03

Other Blackwell cards

The same generation in other memory sizes. Memory is what decides which models fit.

GeForce RTX 507012 GB · less memory GeForce RTX 508016 GB · less memory GeForce RTX 5060 Ti 16GB16 GB · less memory GeForce RTX 5070 Ti16 GB · less memory RTX PRO 6000 Blackwell96 GB · more memory B200 (SXM 192GB)192 GB · more memory

Something wrong on this page? Tell us