Aya Vision 32B on NVIDIA RTX Spark N1X (6144-core GPU) (48 GB)

Can the NVIDIA RTX Spark N1X (6144-core GPU) (48 GB) run Aya Vision 32B?

Yes, it runs well

Runs well. At Q4_K_M it needs about 24.7 GB of 32.2 GB usable, with an estimated speed of 11.1 tok/s.

Best quant: Q4_K_M
Generation speed: 11.1 tok/s
Prompt processing: 626 tok/s
First token (1K prompt): 1.6 s
Largest safe context: 16K

Best app to run it on the NVIDIA RTX Spark N1X (6144-core GPU) (48 GB)

On Linux

Docker Model Runner

Command line + local API · runs on llama.cpp, vLLM

Handy if you already work in Docker.

docker model run hf.co/CohereLabs/aya-vision-32b

Text Generation WebUI

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 Aya Vision 32B

Original weights · Hugging Face

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

huggingface.co/CohereLabs/aya-vision-32b (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 57Good quality (B) · 57 of 100: how capable the model is at Q4_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 Q4_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 well: How well it runs on the NVIDIA RTX Spark N1X (6144-core GPU) (48 GB): 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.	25.7 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	7.9 / 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 score	73.6 / 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 Spark N1X (6144-core GPU) (48 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	17.8 GB	32.2 GB	18.2 tok/s	Runs well	42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q3_K_M`	20.8 GB	32.2 GB	14.4 tok/s	Runs well	50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q4_K_M`	24.7 GB	32.2 GB	11.1 tok/s	Runs well	57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	28.0 GB	32.2 GB	9.2 tok/s	Slowtight fit	58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q6_K`	31.7 GB	32.2 GB	7.7 tok/s	Slowtight fit	59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	39.6 GB	32.2 GB	4.8 tok/s	Slowfar over GPU memory limit	60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	70.8 GB	32.2 GB	—	Won't run	60Good quality (B) · 60 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

58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q5_K_M · 54.8 tok/s · Runs great
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q4_K_M · 37.3 tok/s · Runs well (tight fit)
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q4_K_M · 34.7 tok/s · Runs well (tight fit)
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4_K_M · 30.6 tok/s · Runs well (tight fit)
59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q6_K · 46.1 tok/s · Runs great
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q4_K_M · 17.4 tok/s · Runs well

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.