Aya Vision 32B on Intel Core i5-12400 NAS (32 GB)
Can the Intel Core i5-12400 NAS (32 GB) run Aya Vision 32B?
Barely: it runs very slowly (tight fit)
Very slow (tight fit). At Q4_K_M it needs about 24.3 GB of 26.2 GB usable, with an estimated speed of 1.6 tok/s.
- Best quant
Q4_K_M- Generation speed
- 1.6 tok/s
- Prompt processing
- 8.1 tok/s
- First token (1K prompt)
- 125.7 s
- Largest safe context
- 16K
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)
How it’s rated
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 quality | 25.7 / 45 | |
|---|---|---|
| Memory fit | 24.0 / 25 | |
| Speed | 3.0 / 15 | |
| Memory use | 15.0 / 15 | |
| Match score | 67.6 / 100 |
Every quantization on the Intel Core i5-12400 NAS (32 GB)
| Quant | Memory needed | Available | Speed | Runs | Quality | Download |
|---|---|---|---|---|---|---|
Q2_K | 17.3 GB | 26.2 GB | 2.6 tok/s | Very slow | 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q3_K_M | 20.3 GB | 26.2 GB | 2.0 tok/s | Very slow | 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q4_K_M | 24.3 GB | 26.2 GB | 1.6 tok/s | Very slowtight fit | 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q5_K_M | 27.6 GB | 26.2 GB | 1.1 tok/s | Very slowover memory limit | 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q6_K | 31.2 GB | 26.2 GB | — | Won't run | 59Good quality (B) · 59 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 | 39.2 GB | 26.2 GB | — | Won't run | 60Good quality (B) · 60 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. | All files (opens in a new tab) |
F16 | 70.3 GB | 26.2 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
-
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
-
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
-
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
-
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
-
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)
Quick answers
How much memory does Aya Vision 32B need on the Intel Core i5-12400 NAS 32GB?
At Q4_K_M it needs about 24.3 GB. The Intel Core i5-12400 NAS 32GB has 26.2 GB usable.
How fast is Aya Vision 32B on the Intel Core i5-12400 NAS 32GB?
About 1.6 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.
Which quantization of Aya Vision 32B should I use on the Intel Core i5-12400 NAS 32GB?
Q4_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.