Yes, but only at Q3_K_M (about 15 GB of 16 GB), which costs noticeable quality, at roughly 14 tokens/s.
- best quant
- Q3_K_M
- needs
- 15 GB
- usable
- 16 GB
- est. speed
- ~14 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the GLiDE-27B page →
Every quantisation of GLiDE-27B on the Tesla T4
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 11 GB | fits | ~21 tok/s |
| Q3_K_M pick | 15 GB | fits | ~14 tok/s |
| Q4_K_M | 19 GB | offload | ~6.9 tok/s |
| Q5_K_M | 21 GB | offload | ~4.8 tok/s |
| Q6_K | 24 GB | offload | ~3.4 tok/s |
| Q8_0 | 30 GB | offload | ~2.1 tok/s |
| FP16 / BF16 | 54 GB | too big | — |
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 GLiDE-27B on the Tesla T4
Using Q3_K_M, the best fit for Tesla T4.
llama-server -hf kingjones777/GLiDE-27B-ROCmFP4-STRIX-GGUF:Q3_K_MDownloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
vllm serve fastino/GLiDE-27Bservices:
vllm:
image: vllm/vllm-openai:latest
command: fastino/GLiDE-27B
ports:
- "8000:8000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 8000.
sglang serve fastino/GLiDE-27B --host 0.0.0.0 --port 30000services:
sglang:
image: lmsysorg/sglang:latest
command: sglang serve fastino/GLiDE-27B --host 0.0.0.0 --port 30000
ports:
- "30000:30000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 30000.
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="fastino/GLiDE-27B", 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 →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 12.2B | Q6_K | ≈13 GBFits in memory | ~18 tok/s | |
| 19.4BA3B | Q4_K_M | ≈13 GBFits in memory | ~97 tok/s | |
| 9.7B | Q8_0 | ≈11 GBFits in memory | ~17 tok/s | |
| 13.2B | Q6_K | ≈13 GBFits in memory | ~16 tok/s | |
| 8.8B | Q8_0 | ≈10 GBFits in memory | ~19 tok/s | |
| 10.7B | Q8_0 | ≈12 GBFits in memory | ~16 tok/s |
Other GPUs that run GLiDE-27B
Frequently asked questions
- Can the Tesla T4 run GLiDE-27B?
- Yes, but only at Q3_K_M (about 15 GB of 16 GB), which costs noticeable quality, at roughly 14 tokens/s.
- How fast does GLiDE-27B run on the Tesla T4?
- An estimate from memory bandwidth gives about 14 tokens/s at Q3_K_M.
- Which quantisation of GLiDE-27B should I use on the Tesla T4?
- Q3_K_M: the largest one that fits. Expected quality: noticeable loss 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.