Can the Tesla T4 run UserLM-2.0?
UserLM-2.0·8B·Tesla T4·16 GB VRAM
Yes. The Tesla T4 runs UserLM-2.0 fully in VRAM at Q8_0 (about 9.8 GB of 16 GB), at roughly 21 tokens/s.
- best quant
- Q8_0
- needs
- 9.8 GB
- usable
- 16 GB
- est. speed
- ~21 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the UserLM-2.0 page →
Every quantisation of UserLM-2.0 on the Tesla T4
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 4.1 GB | fits | ~67 tok/s |
| Q3_K_M | 5.3 GB | fits | ~45 tok/s |
| Q4_K_M | 6.3 GB | fits | ~36 tok/s |
| Q5_K_M | 7.1 GB | fits | ~31 tok/s |
| Q6_K | 8.0 GB | fits | ~27 tok/s |
| Q8_0 pick | 9.8 GB | fits | ~21 tok/s |
| FP16 / BF16 | 17 GB | offload | ~8.4 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 UserLM-2.0 on the Tesla T4
Using Q8_0, the best fit for Tesla T4.
llama-server -hf liodon-ai/UserLM-2.0-imatrix-GGUF:Q8_0Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
vllm serve microsoft/UserLM-2.0 vllm serve liodon-ai/UserLM-2.0-FP8services:
vllm:
image: vllm/vllm-openai:latest
command: microsoft/UserLM-2.0
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 microsoft/UserLM-2.0 --host 0.0.0.0 --port 30000services:
sglang:
image: lmsysorg/sglang:latest
command: sglang serve microsoft/UserLM-2.0 --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("text-generation", model="microsoft/UserLM-2.0", dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Explain self-hosting in one paragraph."}]
out = pipe(messages, max_new_tokens=512)
print(out[0]["generated_text"][-1]["content"])Chat models that fit the Tesla T4 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 8B | Q8_0 | ≈9.8 GBFits in memory | ~21 tok/s | |
| 8.2B | Q8_0 | ≈10 GBFits in memory | ~20 tok/s | |
| 8B | Q8_0 | ≈9.8 GBFits in memory | ~21 tok/s | |
| 7.6B | Q8_0 | ≈8.9 GBFits in memory | ~22 tok/s | |
| 9.4B | Q8_0 | ≈11 GBFits in memory | ~18 tok/s | |
| 7.2B | Q8_0 | ≈9.0 GBFits in memory | ~23 tok/s |
Other GPUs that run UserLM-2.0
Frequently asked questions
- Can the Tesla T4 run UserLM-2.0?
- Yes. The Tesla T4 runs UserLM-2.0 fully in VRAM at Q8_0 (about 9.8 GB of 16 GB), at roughly 21 tokens/s.
- How fast does UserLM-2.0 run on the Tesla T4?
- An estimate from memory bandwidth gives about 21 tokens/s at Q8_0.
- Which quantisation of UserLM-2.0 should I use on the Tesla T4?
- 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.