Hardware / NVIDIA /RTX 6000 Ada

NVIDIA · GPU

RTX 6000 Ada

Runs 134 models fully in memory, 14 more with CPU offload.

Memory

48 GB

Bandwidth

960 GB/s

Runs

134

01

Specifications

Memory

48 GB

Decides which models fit at all.

Memory bandwidth

960 GB/s

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

Compute

91.1 TFLOPS

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

Power draw

300 W

At full load, for sizing a power supply.

MSRP

$6,800

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

Released

Dec 3, 2022

Architecture

Ada Lovelace

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 8B8.8B131K123 tok/sFits in memory Qwen3.6 35B A3B36B131K306 tok/sFits in memory Gemma 4 26B A4B25.8B66K230 tok/sFits in memory Qwen3.5-9B9.7B262K131 tok/sFits in memory Nemotron 3 Nano 30B A3B31.6B262K306 tok/sFits in memory Ministral 3 8B 25128.9B262K121 tok/sFits in memory Ministral 3 3B 25123.8B131K190 tok/sFits in memory gpt-oss-safeguard-20b21.5B131K299 tok/sFits in memory Granite 4.0 Micro3.2B66K226 tok/sFits in memory Qwen3 VL 8B Thinking8.8B131K123 tok/sFits in memory Qwen3 VL 30B A3B Thinking31.1B131K306 tok/sFits in memory UI-TARS 7B8.3B66K130 tok/sFits in memory Llama 3.2 3B Instruct3.2B131K337 tok/sFits in memory Qwen3.5-35B-A3B36B262K359 tok/sFits in memory Qwen3 VL 8B Instruct8.8B262K123 tok/sFits in memory Qwen3 VL 30B A3B Instruct31.1B66K205 tok/sFits in memory Qwen3 30B A3B Thinking 250730.5B66K205 tok/sFits in memory Qwen3 Coder 30B A3B Instruct30.5B66K205 tok/sFits in memory Qwen3 30B A3B Instruct 250730.5B262K359 tok/sFits in memory Qwen3 8B8.2B131K155 tok/sFits in memory Gemma 3 4B4.3B131K251 tok/sFits in memory Llama 3.1 8B Instruct8B131K158 tok/sFits in memory Granite 4.2 8B8.8B131K123 tok/sFits in memory Nemotron 3.5 Content Safety4.3B131K251 tok/sFits in memory Gemma 3n 4B7.8B33K138 tok/sFits in memory Llama 3.2 1B Instruct1.2B33K900 tok/sFits in memory Qwen2.5 7B Instruct7.6B33K142 tok/sFits in memory Llama Guard 4 12B12B262K106 tok/sFits in memory Gemma 3 12B12.2B131K104 tok/sFits in memory Rocinante 12B12.2B66K104 tok/sFits in memory Mistral Nemo12.2B131K104 tok/sFits in memory Reka Edge7.1B16K152 tok/sFits in memory Ministral 3 14B 251213.9B131K91 tok/sFits in memory UnslopNemo 12B12.2B33K104 tok/sFits in memory Qwen3 14B14.8B131K86 tok/sFits in memory Llama 3 8B Lunaris8B8K135 tok/sFits in memory Hy-MT2-1.8B2B8K538 tok/sFits in memory Hy-MT2-30B-A3B30.1B8K306 tok/sFits in memory Hy-MT2-7B8B8K135 tok/sFits in memory Phi 414.7B16K86 tok/sFits in memory MythoMax 13B13B8K97 tok/sFits in memory Reka Flash 320.9B66K61 tok/sFits in memory Cydonia 24B V4.123.6B131K54 tok/sFits in memory Uncensored24B66K53 tok/sFits in memory Mistral Small 3.2 24B24B131K53 tok/sFits in memory Mistral Small 3.1 24B24B66K53 tok/sFits in memory Gemma 3 27B27.4B262K46 tok/sFits in memory ReMM SLERP 13B13B4K97 tok/sFits in memory Ternary Bonsai 2 27B27B262K47 tok/sFits in memory Qwen3.5-27B27.8B66K46 tok/sFits in memory Qwen3.6 27B27.8B66K46 tok/sFits in memory Muse Glimmer 30B29.8B131K43 tok/sFits in memory Qwen3.8 27B27.8B66K46 tok/sFits in memory Olmo 3 32B Think32.2B66K39 tok/sFits in memory Qwen3 32B32.8B66K39 tok/sFits in memory Mistral Small 323.6B33K54 tok/sFits in memory GLM 4.7 Flash31.2B66K35 tok/sFits in memory Qwen3 VL 32B Instruct33.4B66K38 tok/sFits in memory Nemotron 3.5 Lightning31.6B262K34 tok/sFits in memory Nex-N2-Mini35.1B262K31 tok/sFits in memory Laguna XS 2.133.4B131K32 tok/sFits in memory Nex-N2.5-Mini35.1B262K31 tok/sFits in memory Voxtral Small 24B 250724.3B16K52 tok/sFits in memory Qwen2.5 Coder 32B Instruct32.8B33K39 tok/sFits in memory Skyfall 36B V236.9B33K34 tok/sFits in memory Gemma 4 31B31.3B16K41 tok/sFits in memory Gemma 2 27B27.2B8K47 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.en20M36141 tok/sFits in memory Niagara 38m Batch.en38M19022 tok/sFits in memory Higgs Audio v3 8b STT v28.9B142 tok/sFits in memory Higgs Audio v3 STT2.7B268 tok/sFits in memory Cohere Transcribe 03 20262.1B344 tok/sFits in memory Distil Large v3.50.8B904 tok/sFits in memory Lite Whisper Large v3 Acc1.4B771 tok/sFits in memory Owsm CTC v3.1 1B1.1B1152 tok/sFits in memory Owsm CTC v3.2 ft 1B1B723 tok/sFits in memory Owsm CTC v4 1B1B1267 tok/sFits in memory Hubert Large Ls960 ft0.3B2259 tok/sFits in memory MMS 1b All1B1080 tok/sFits in memory Wav2vec2 Large 960h Lv60 Self0.3B2259 tok/sFits in memory Hojo ASR V15.2B209 tok/sFits in memory Granite 4.0 1b Speech2.3B314 tok/sFits in memory Granite Speech 3.3 2b3B422 tok/sFits in memory Granite Speech 3.3 8b8.6B147 tok/sFits in memory Granite Speech 4.1 2b2.3B551 tok/sFits in memory Granite Speech 4.1 2b NAR2.3B551 tok/sFits in memory STT 2.6b en2.6B487 tok/sFits in memory Phi 4 Multimodal Instruct5.6B131K129 tok/sFits in memory VibeVoice ASR HF8.3B130 tok/sFits in memory Voxtral Mini 3B 25074.7B154 tok/sFits in memory Voxtral Mini 4B Realtime 26024.4B164 tok/sFits in memory Canary 180m Flash0.2B5999 tok/sFits in memory Canary 1b1B723 tok/sFits in memory Canary 1b Flash0.8B904 tok/sFits in memory Canary 1b v21B723 tok/sFits in memory Canary Qwen 2.5b2.6B278 tok/sFits in memory Nemotron 3.5 ASR Streaming 0.6b0.6B1205 tok/sFits in memory Nemotron Speech Streaming en 0.6b0.6B1205 tok/sFits in memory Parakeet CTC 0.6b0.6B2111 tok/sFits in memory Parakeet CTC 1.1b1.1B657 tok/sFits in memory Parakeet RNNT 0.6b0.6B1205 tok/sFits in memory Parakeet RNNT 1.1b1.1B1152 tok/sFits in memory Parakeet TDT CTC 110m0.1B6571 tok/sFits in memory Parakeet TDT 0.6b v20.6B1800 tok/sFits in memory Parakeet TDT 0.6b v30.6B1205 tok/sFits in memory Parakeet TDT 1.1b1.1B657 tok/sFits in memory Nyra Health CrisperWhisper1.6B452 tok/sFits in memory Whisper Large v31.5B720 tok/sFits in memory Whisper Large v3 Turbo0.8B1584 tok/sFits in memory MOSS Transcribe Diarize0.9B803 tok/sFits in memory Qwen3 ASR 0.6B0.9B1408 tok/sFits in memory Qwen3 ASR 0.6B HF0.8B1584 tok/sFits in memory Qwen3 ASR 1.7B2.3B470 tok/sFits in memory Qwen3 ASR 1.7B HF2B361 tok/sFits in memory Zipformer cr CTC Transducer XL 290M0.3B3723 tok/sFits in memory Zipformer Transducer XL 290M0.3B2493 tok/sFits in memory ASR Conformer Largescaleasr0.5B2639 tok/sFits in memory GLM ASR Nano 25122.3B470 tok/sFits in memory Granite Speech 5.0 470m Turboctc0.5B2160 tok/sFits in memory Granite Speech 5.0 470m Turboctc nc0.5B2534 tok/sFits in memory Fun ASR Nano 2512 HF0.8B1584 tok/sFits in memory Gemma 4 E2B it5.1B142 tok/sFits in memory Gemma 4 E4B it8B131K135 tok/sFits in memory Niagara 9m Batch.en9M80314 tok/sFits in memory Niagara 84m Batch.en84M15081 tok/sFits in memory ARK ASR 0.6B1.3B33K975 tok/sFits in memory ARK ASR 3B4.1B33K309 tok/sFits in memory Audio8 ASR 0.1B0.3B33K2409 tok/sFits in memory MOSS Transcribe Preview 2B2.4B33K528 tok/sFits in memory Gemma 4 12B it12B106 tok/sFits in memory Moonshine Streaming Medium0.3B4K4223 tok/sFits in memory Moonshine Streaming Small0.1B4K7228 tok/sFits in memory Moonshine Streaming Tiny0B4Kno speed estimateFits in memory Moonshine Tiny0B194no speed estimateFits in memory

Runs only by spilling into system memory14 modelsThese load, but part of the weights sits in ordinary system memory, which is far slower than the chip.

Qwen3 Coder Next79.7B—no speed estimateSpills to system RAM Qwen3 Next 80B A3B Thinking81.3B—no speed estimateSpills to system RAM Hermes 4 70B70.6B—no speed estimateSpills to system RAM Hunyuan A13B Instruct80.4B—no speed estimateSpills to system RAM Qwen2.5 VL 72B Instruct73.4B—no speed estimateSpills to system RAMest Llama 3.3 Euryale 70B70.6B—no speed estimateSpills to system RAM Magnum v4 72B72.7B—no speed estimateSpills to system RAM Llama 3.1 Euryale 70B v2.270.6B—no speed estimateSpills to system RAMest Qwen3 Next 80B A3B Instruct81.3B—no speed estimateSpills to system RAM R1 Distill Llama 70B70.6B—no speed estimateSpills to system RAMest Qwen2.5 72B Instruct72.7B—no speed estimateSpills to system RAMest Hermes 3 70B Instruct70.6B—no speed estimateSpills to system RAM Llama 3.1 70B Instruct70.6B—no speed estimateSpills to system RAMest Llama 3.3 70B Instruct70.6B—no speed estimateSpills to system RAMest

Too large for this device76 modelsThe weights do not fit even with part of them offloaded to system memory. Closest calls first.

Nemotron 3 Super124B—no speed estimateToo large GLM 4.5V108B—no speed estimateToo large Llama 4 Scout109B—no speed estimateToo large GLM 4.5 Air111B—no speed estimateToo large Command A111B—no speed estimateToo large Laguna S 2.1118B—no speed estimateToo large gpt-oss-120b120B—no speed estimateToo large Mistral Small 4119B—no speed estimateToo large Devstral 2 2512125B—no speed estimateToo large Mixtral 8x22B Instruct141B—no speed estimateToo large GLM 4.6V108B—no speed estimateToo large Ling-2.6-flash107B—no speed estimateToo large Qwen3.5-122B-A10B125B—no speed estimateToo large Mistral Medium 3.5128B—no speed estimateToo large Ling-3.0-flash128B—no speed estimateToo large MiniMax M2.7229B—no speed estimateToo large Step 3.5 Flash199B—no speed estimateToo large Qwen3 VL 235B A22B Thinking236B—no speed estimateToo large Step 3.7 Flash201B—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 GLM 4.5358B—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 MiniMax M2.1229B—no speed estimateToo large MiniMax M2229B—no speed estimateToo large Qwen3 235B A22B Thinking 2507235B—no speed estimateToo large Qwen3 235B A22B Instruct 2507235B—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 MiniMax M3427B—no speed estimateToo large Inkling Small266B—no speed estimateToo large Trinity Large Thinking399B—no speed estimateToo large Jamba Large 1.7399B—no speed estimateToo large Hermes 4 405B406B—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 Nemotron 3 Ultra561B—no speed estimateToo large Qwen3 Coder 480B A35B480B—no speed estimateToo large Llama 4 Maverick402B—no speed estimateToo large Qwen3.5 397B A17B403B—no speed estimateToo large Hermes 3 405B Instruct406B—no speed estimateToo large ERNIE 4.5 VL 424B A47B424B—no speed estimateToo large GLM 5.1754B—no speed estimateToo large GLM 5.2753B—no speed estimateToo large MiniMax-01456B—no speed estimateToo large R1 0528685B—no speed estimateToo large DeepSeek V3685B—no speed estimateToo large DeepSeek V3.1685B—no speed estimateToo large GLM 5754B—no speed estimateToo large DeepSeek V4.1 Flash763B—no speed estimateToo large MiMo-V2.5-Pro1T—no speed estimateToo large Kimi K2 07111T—no speed estimateToo large Ring-2.6-1T1T—no speed estimateToo large Ling-2.6-1T1T—no speed estimateToo large Kimi K2.7 Code1.1T—no speed estimateToo large DeepSeek V3.1 Terminus685B—no speed estimateToo large DeepSeek V3 0324685B—no speed estimateToo large DeepSeek V3.2685B—no speed estimateToo large DeepSeek V3.2 Exp685B—no speed estimateToo large Kimi K2 Thinking1.1T—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 Inkling952B—no speed estimateToo large Kimi K2 09051T—no speed estimateToo large Qwen3.8 2.4T A95B2.4T—no speed estimateToo large Kimi K32.8T—no speed estimateToo large DeepSeek V4 Pro1.6T—no speed estimateToo large LongCat 2.01.8T—no speed estimateToo large

224 models have a verdict on this device: 134 fit in memory, 14 spill into system memory and 76 are too large. Every one of them is on this page.

03

Other Ada Lovelace cards

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

GeForce RTX 4060 8GB8 GB · less memory GeForce RTX 4070 SUPER12 GB · less memory GeForce RTX 4060 Ti 16GB16 GB · less memory GeForce RTX 4070 Ti SUPER16 GB · less memory GeForce RTX 4080 SUPER16 GB · less memory GeForce RTX 409024 GB · less memory L40S48 GB · same memory

Something wrong on this page? Tell us