on

Can the NVIDIA RTX 6000 Ada Generation run Qwen2-VL 72B Instruct?

53Fair quality (C) · 53 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs well (tight fit)

Runs well (tight fit). At Q3_K_M it needs about 41.7 GB of 48.0 GB usable, with an estimated speed of 20.8 tok/s.

Best quant
Q3_K_M
Generation speed
20.8 tok/s
Prompt processing
894 tok/s
First token (1K prompt)
1.1 s
Largest safe context
26K

Best app to run it on the NVIDIA RTX 6000 Ada Generation

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

  • Point-and-click: search, download and chat in one window.

Open Qwen2-VL 72B Instruct in LM Studio

  • llama.cpp Usually the first to support new model architectures.
  • Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

On Linux

LM Studio

Desktop app · runs on llama.cpp, MLX

  • Point-and-click: search, download and chat in one window.

Open Qwen2-VL 72B Instruct in LM Studio

  • llama.cpp Usually the first to support new model architectures.
  • Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Qwen2-VL 72B Instruct

Recommended for the NVIDIA RTX 6000 Ada Generation: Q3_K_M. Every other quantization has its own download link in the table below.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q3_K_M file (opens in a new tab)

huggingface.co/bartowski/Qwen2-VL-72B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/bartowski/Qwen2-VL-72B-Instruct-GGUF:Q3_K_M

Original weights · Hugging Face

Full-precision files from Alibaba, for fine-tuning, vLLM, Transformers.

huggingface.co/Qwen/Qwen2-VL-72B-Instruct (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 53Fair quality (C) · 53 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q3_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs welltight fit
How well it runs on the NVIDIA RTX 6000 Ada Generation: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.24.2 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.10.8 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.15.0 / 15
Match score74.0 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA RTX 6000 Ada Generation

Quant Memory needed Available Speed Runs Quality Download
Q2_K 35.0 GB 48.0 GB 26.4 tok/s Runs well 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q3_K_M 41.7 GB 48.0 GB 20.8 tok/s Runs welltight fit 53Fair quality (C) · 53 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q4_K_M 50.5 GB 48.0 GB 9.2 tok/s Slowoffloads to RAM 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 57.8 GB 48.0 GB 3.8 tok/s Slowoffloads to RAM 62Good quality (B) · 62 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q6_K 65.9 GB 48.0 GB 2.2 tok/s Very slowoffloads to RAM 63Good quality (B) · 63 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q8_0 83.5 GB 48.0 GB — Won't run 64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
F16 153 GB 48.0 GB — Won't run 64Good quality (B) · 64 of 100: how capable the model is at F16, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

Quick answers

How much memory does Qwen2-VL 72B Instruct need on the NVIDIA RTX 6000 Ada Generation 48GB?

At Q3_K_M it needs about 41.7 GB. The NVIDIA RTX 6000 Ada Generation 48GB has 48.0 GB usable.

How fast is Qwen2-VL 72B Instruct on the NVIDIA RTX 6000 Ada Generation 48GB?

About 20.8 tok/s at Q3_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Qwen2-VL 72B Instruct should I use on the NVIDIA RTX 6000 Ada Generation 48GB?

Q3_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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?