on

Can the AMD Radeon PRO W7800 48GB run Llama 3.2 90B Vision Instruct?

46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs well (tight fit)

Runs well (tight fit). At Q2_K it needs about 41.8 GB of 48.0 GB usable, with an estimated speed of 16.9 tok/s.

Best quant
Q2_K
Generation speed
16.9 tok/s
Prompt processing
633 tok/s
First token (1K prompt)
1.6 s
Largest safe context
22K

Best app to run it on the AMD Radeon PRO W7800 48GB

On Windows

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

  • One command with Ollama’s own build of this model.
  • Serves an OpenAI-compatible API that other apps and coding tools can use.
ollama run llama3.2-vision:90b

On Linux

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

  • One command with Ollama’s own build of this model.
  • Serves an OpenAI-compatible API that other apps and coding tools can use.
ollama run llama3.2-vision:90b

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 Llama 3.2 90B Vision Instruct

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run llama3.2-vision:90b

Original weights · Hugging Face

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

huggingface.co/meta-llama/Llama-3.2-90B-Vision-Instruct (opens in a new tab)

Free Hugging Face account needed: request access on the model page, and Meta approves it (usually within minutes to a few hours).

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

How it’s rated

Quality 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q2_K, 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 AMD Radeon PRO W7800 48GB: 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.20.8 / 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.9.8 / 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 score69.5 / 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 AMD Radeon PRO W7800 48GB

Quant Memory needed Available Speed Runs Quality Download
Q2_K 41.8 GB 48.0 GB 16.9 tok/s Runs welltight fit 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q3_K_M 49.8 GB 48.0 GB 9.4 tok/s Slowoffloads to RAM 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q4_K_M 60.4 GB 48.0 GB 3.1 tok/s Slowoffloads to RAM 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.
Q5_K_M 69.3 GB 48.0 GB — Won't run 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q6_K 79.0 GB 48.0 GB — Won't run 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q8_0 100 GB 48.0 GB — Won't run 66Good quality (B) · 66 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.
F16 184 GB 48.0 GB — Won't run 66Good quality (B) · 66 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 Llama 3.2 90B Vision Instruct need on the PRO W7800 48GB?

At Q2_K it needs about 41.8 GB. The PRO W7800 48GB has 48.0 GB usable.

How fast is Llama 3.2 90B Vision Instruct on the PRO W7800 48GB?

About 16.9 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Llama 3.2 90B Vision Instruct should I use on the PRO W7800 48GB?

Q2_K. 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?