selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

microsoft logo

Can the Tesla T4 run Mage-VL-Cowork?

Mage-VL-Cowork·4.7B·Tesla T4·16 GB VRAM

Saved in this browser, used on every model page.
Yes

Yes. The Tesla T4 runs Mage-VL-Cowork fully in VRAM at FP16 / BF16 (about 10 GB of 16 GB), at roughly 19 tokens/s.

best quant
FP16 / BF16
needs
10 GB
usable
16 GB
est. speed
~19 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 Tesla T4

QuantQualityMemoryFitSpeed
Q2_K Heavy loss3.1 GBfits~113 tok/s
Q3_K_M Noticeable loss3.9 GBfits~76 tok/s
Q4_K_M Small loss4.3 GBfits~61 tok/s
Q5_K_M Near-lossless4.9 GBfits~52 tok/s
Q6_K Near-lossless5.4 GBfits~45 tok/s
Q8_0 Lossless6.2 GBfits~35 tok/s
FP16 / BF16 pickLossless10 GBfits~19 tok/s

Speed is a bandwidth-based estimate for generating text (320 GB/s); prompt processing and long contexts are slower.

Measured speed on the Tesla T4

No community reports for this pair yet.

Report your own speed →

Run Mage-VL-Cowork on the Tesla T4

Transformers · Ask about an imagedocs
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 Tesla T4 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
4.7BQ8_0≈5.9 GBFits in memory~36 tok/sCommercial OK
4.3BQ8_0≈5.2 GBFits in memory~39 tok/sConditions
4.4BQ8_0≈5.8 GBFits in memory~37 tok/sCommercial OK
5BQ8_0≈5.6 GBFits in memory~33 tok/sConditions
4.3BQ8_0≈5.6 GBFits in memory~39 tok/sConditions
3.8BQ8_0≈4.0 GBFits in memory~44 tok/sNon-commercial

Other GPUs that run Mage-VL-Cowork

Frequently asked questions

Can the Tesla T4 run Mage-VL-Cowork?
Yes. The Tesla T4 runs Mage-VL-Cowork fully in VRAM at FP16 / BF16 (about 10 GB of 16 GB), at roughly 19 tokens/s.
How fast does Mage-VL-Cowork run on the Tesla T4?
An estimate from memory bandwidth gives about 19 tokens/s at FP16 / BF16.
Which quantisation of Mage-VL-Cowork should I use on the Tesla T4?
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.