Can the RTX A4000 run Mage-VL-Cowork?
Mage-VL-Cowork·4.7B·RTX A4000·16 GB VRAM
Yes. The RTX A4000 runs Mage-VL-Cowork fully in VRAM at FP16 / BF16 (about 10 GB of 16 GB), at roughly 26 tokens/s.
- best quant
- FP16 / BF16
- needs
- 10 GB
- usable
- 16 GB
- est. speed
- ~26 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Mage-VL-Cowork page →
Every quantisation of Mage-VL-Cowork on the RTX A4000
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 3.1 GB | fits | ~158 tok/s |
| Q3_K_M | 3.9 GB | fits | ~106 tok/s |
| Q4_K_M | 4.3 GB | fits | ~86 tok/s |
| Q5_K_M | 4.9 GB | fits | ~73 tok/s |
| Q6_K | 5.4 GB | fits | ~63 tok/s |
| Q8_0 | 6.2 GB | fits | ~49 tok/s |
| FP16 / BF16 pick | 10 GB | fits | ~26 tok/s |
Speed is a bandwidth-based estimate for generating text (448 GB/s); prompt processing and long contexts are slower.
Measured speed on the RTX A4000
No community reports for this pair yet.
Report your own speed →Run Mage-VL-Cowork on the RTX A4000
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="microsoft/Mage-VL-Cowork", dtype="auto", device_map="auto")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
{"type": "text", "text": "Describe this image."},
],
}
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])Vision models that fit the RTX A4000 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 4.7B | Q8_0 | ≈5.9 GBFits in memory | ~50 tok/s | |
| 4.3B | Q8_0 | ≈5.2 GBFits in memory | ~54 tok/s | |
| 4.4B | Q8_0 | ≈5.8 GBFits in memory | ~52 tok/s | |
| 5B | Q8_0 | ≈5.6 GBFits in memory | ~47 tok/s | |
| 4.3B | Q8_0 | ≈5.6 GBFits in memory | ~54 tok/s | |
| 3.8B | Q8_0 | ≈4.0 GBFits in memory | ~62 tok/s |
Other GPUs that run Mage-VL-Cowork
Frequently asked questions
- Can the RTX A4000 run Mage-VL-Cowork?
- Yes. The RTX A4000 runs Mage-VL-Cowork fully in VRAM at FP16 / BF16 (about 10 GB of 16 GB), at roughly 26 tokens/s.
- How fast does Mage-VL-Cowork run on the RTX A4000?
- An estimate from memory bandwidth gives about 26 tokens/s at FP16 / BF16.
- Which quantisation of Mage-VL-Cowork should I use on the RTX A4000?
- FP16 / BF16: the largest one that fits. Expected quality: lossless compared with the full-precision weights.
Memory and speed are estimates from the model's size and the card's memory bandwidth; real numbers depend on the runtime, drivers and context length. Community figures are medians of user reports.