NVIDIA RTX 4000 Ada Generation

Hardware · NVIDIA

What AI models can the NVIDIA RTX 4000 Ada Generation run?

VRAM
20.0 GB
Usable for models
20.0 GB
Memory bandwidth
360 GB/s
FP16 compute
26.7 TFLOPS
Released
2023
Launch price
$1,250
491 / 621 LLMs run Best: Gemma 4 26B-A4B 58 / 61 Image models run Best: FLUX 3 Image Klein 22 / 43 Video models run Best: LTX-2.5 (22B, video + audio) 68 / 70 Decision models run Best: Qwen3 Reranker 4B

More about this hardware

MakerNVIDIA
TypeWorkstation / datacenter graphics card
InterfacePCIe 4.0

Apps that run models well on the NVIDIA RTX 4000 Ada Generation

Windows

  1. OllamaOne command with Ollama’s own build of this model.
  2. LM StudioPoint-and-click: search, download and chat in one window.
  3. llama.cppUsually the first to support new model architectures.
  4. JanPoint-and-click: search, download and chat in one window.

Linux

  1. OllamaOne command with Ollama’s own build of this model.
  2. LM StudioPoint-and-click: search, download and chat in one window.
  3. llama.cppUsually the first to support new model architectures.
  4. JanPoint-and-click: search, download and chat in one window.

For a typical model that fits in memory. Each model page picks the best app for that model on this hardware. All apps

24 products with the NVIDIA RTX 4000 Ada Generation

Best LLMs for the NVIDIA RTX 4000 Ada Generation

Quality Model Quant Memory Speed Runs
87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4BGoogle Q4_K_M 17.7 GB 83.6 tok/s Runs welltight fit
83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B)KRAFTON Q4_K_M 19.2 GB 76.4 tok/s Runs welltight fit
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3BAlibaba Q3_K_M 19.4 GB 118 tok/s Runs welltight fit
90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.8 27BAlibaba Q4_K_M 19.1 GB 15.9 tok/s Runs welltight fit
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3BOpenBMB Q3_K_M 19.0 GB 118 tok/s Runs welltight fit
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3BAlibaba Q3_K_M 19.4 GB 118 tok/s Runs welltight fit
77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B)Nex-AGI Q3_K_M 19.0 GB 118 tok/s Runs welltight fit
89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 27BAlibaba Q4_K_M 19.1 GB 15.9 tok/s Runs welltight fit
76Great quality (A) · 76 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B)Kuaishou Q3_K_M 18.8 GB 118 tok/s Runs welltight fit
76Great quality (A) · 76 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Sage-A1.5 35B-A3BInternScience Q3_K_M 19.4 GB 118 tok/s Runs welltight fit
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 27BAlibaba Q4_K_M 19.1 GB 15.9 tok/s Runs welltight fit
75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 35B-A3BDeepReinforce Q3_K_M 19.4 GB 118 tok/s Runs welltight fit

Best Image models for the NVIDIA RTX 4000 Ada Generation

Quality Model Quant Memory Speed Runs
89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. FLUX 3 Image KleinBlack Forest Labs FP8 12.4 GB 12 s Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. ERNIE-Image TurboBaidu Q8 GGUF 15.0 GB 8.6 s Runs great
83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Z-Image TurboAlibaba (Tongyi) Q8 GGUF 13.0 GB 6.7 s Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Krea 2 TurboKrea FP8 15.7 GB 9.5 s Runs greatencoder in RAM
78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 9BBlack Forest Labs Q4 GGUF 16.2 GB 5.0 s Runs great
77Great quality (A) · 77 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 4BBlack Forest Labs Q8 GGUF 10.5 GB 2.7 s Runs great

Best Video models for the NVIDIA RTX 4000 Ada Generation

Quality Model Quant Memory Speed Runs
81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. LTX-2.5 (22B, video + audio)Lightricks Q4 GGUF 16.8 GB 5.5 min Runs wellCPU offload
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. CogVideoX 5BZhipu AI FP8 14.3 GB 6.3 min Runs well
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. CogVideoX 5B I2VZhipu AI FP8 14.9 GB 6.3 min Runs well
49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. LTX-Video 2BLightricks FP8 10.8 GB 52 s Runs great
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. HY-OmniWeaving (8.3B, unified video)Tencent FP8 15.7 GB 19.5 min Slowencoder in RAM

Best Decision models for the NVIDIA RTX 4000 Ada Generation

Quality Model Quant Memory Speed Runs
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Reranker 4BAlibaba Q8_0 6.2 GB 129 ms Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3.5Jina AI F16 3.0 GB 26 ms Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. zerank-2ZeroEntropy Q8_0 6.2 GB 129 ms Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Intern-Decision 4BShanghai AI Lab Q8_0 6.5 GB 85 ms Runs great
84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3Jina AI F16 3.0 GB 26 ms Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Shieldstral 1.0 3BMistral AI Q8_0 5.9 GB 124 ms Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. d1 3BLiquid AI F16 7.9 GB 76 ms Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. mxbai-rerank-large v2Mixedbread F16 4.7 GB 60 ms Runs great

Best LLMs by task on this hardware Open in Model Finder

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?