Can the RTX 4060 run Mage-VL-Cowork?
Mage-VL-Cowork·4.7B·GeForce RTX 4060·8 GB VRAM
Yes. The RTX 4060 runs Mage-VL-Cowork fully in VRAM at Q8_0 (about 6.2 GB of 8.0 GB), at roughly 30 tokens/s.
- best quant
- Q8_0
- needs
- 6.2 GB
- usable
- 8.0 GB
- est. speed
- ~30 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 4060
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 3.1 GB | fits | ~96 tok/s |
| Q3_K_M | 3.9 GB | fits | ~65 tok/s |
| Q4_K_M | 4.3 GB | fits | ~52 tok/s |
| Q5_K_M | 4.9 GB | fits | ~44 tok/s |
| Q6_K | 5.4 GB | fits | ~38 tok/s |
| Q8_0 pick | 6.2 GB | fits | ~30 tok/s |
| FP16 / BF16 | 10 GB | offload | ~8.9 tok/s |
Speed is a bandwidth-based estimate for generating text (272 GB/s); prompt processing and long contexts are slower.
Measured speed on the RTX 4060
No community reports for this pair yet.
Report your own speed →Run Mage-VL-Cowork on the RTX 4060
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 4060 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 4.7B | Q8_0 | ≈5.9 GBFits in memory | ~30 tok/s | |
| 4.3B | Q8_0 | ≈5.2 GBFits in memory | ~33 tok/s | |
| 4.4B | Q8_0 | ≈5.8 GBFits in memory | ~32 tok/s | |
| 5B | Q8_0 | ≈5.6 GBFits in memory | ~28 tok/s | |
| 4.3B | Q8_0 | ≈5.6 GBFits in memory | ~33 tok/s | |
| 4.3B | Q8_0 | ≈5.6 GBFits in memory | ~33 tok/s |
Other GPUs that run Mage-VL-Cowork
Frequently asked questions
- Can the RTX 4060 run Mage-VL-Cowork?
- Yes. The RTX 4060 runs Mage-VL-Cowork fully in VRAM at Q8_0 (about 6.2 GB of 8.0 GB), at roughly 30 tokens/s.
- How fast does Mage-VL-Cowork run on the RTX 4060?
- An estimate from memory bandwidth gives about 30 tokens/s at Q8_0.
- Which quantisation of Mage-VL-Cowork should I use on the RTX 4060?
- Q8_0: 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.