Can the Tesla T4 run Qwen3.8-4B-Distill?
Qwen3.8-4B-Distill·4.7B·Tesla T4·16 GB VRAM
Yes. The Tesla T4 runs Qwen3.8-4B-Distill fully in VRAM at FP16 / BF16 (about 10.0 GB of 16 GB), at roughly 19 tokens/s.
- best quant
- FP16 / BF16
- needs
- 10.0 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 Qwen3.8-4B-Distill page →
Every quantisation of Qwen3.8-4B-Distill on the Tesla T4
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 3.4 GB | fits | ~115 tok/s |
| Q3_K_M | 3.8 GB | fits | ~77 tok/s |
| Q4_K_M | 4.2 GB | fits | ~62 tok/s |
| Q5_K_M | 4.6 GB | fits | ~53 tok/s |
| Q6_K | 5.0 GB | fits | ~46 tok/s |
| Q8_0 | 6.0 GB | fits | ~36 tok/s |
| FP16 / BF16 pick | 10.0 GB | fits | ~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 Qwen3.8-4B-Distill on the Tesla T4
Using FP16 / BF16, the best fit for Tesla T4.
ollama run hf.co/empero-ai/Qwen3.8-4B-Distill-GGUF:BF16 llama-server -hf empero-ai/Qwen3.8-4B-Distill-GGUF:BF16Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get empero-ai/Qwen3.8-4B-Distill-GGUF@BF16Then load it from the LM Studio app or with `lms load`.
vllm serve empero-ai/Qwen3.8-4B-Distillservices:
vllm:
image: vllm/vllm-openai:latest
command: empero-ai/Qwen3.8-4B-Distill
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 empero-ai/Qwen3.8-4B-Distill --host 0.0.0.0 --port 30000services:
sglang:
image: lmsysorg/sglang:latest
command: sglang serve empero-ai/Qwen3.8-4B-Distill --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="empero-ai/Qwen3.8-4B-Distill", 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 |
|---|---|---|---|---|
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~41 tok/s | |
| 3.2B | Q8_0 | ≈4.7 GBFits in memory | ~52 tok/s | |
| 8B | Q8_0 | ≈9.8 GBFits in memory | ~21 tok/s | |
| 3.8B | Q8_0 | ≈5.5 GBFits in memory | ~43 tok/s | |
| 4.1B | Q8_0 | ≈5.9 GBFits in memory | ~40 tok/s | |
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~41 tok/s |
Other GPUs that run Qwen3.8-4B-Distill
Frequently asked questions
- Can the Tesla T4 run Qwen3.8-4B-Distill?
- Yes. The Tesla T4 runs Qwen3.8-4B-Distill fully in VRAM at FP16 / BF16 (about 10.0 GB of 16 GB), at roughly 19 tokens/s.
- How fast does Qwen3.8-4B-Distill run on the Tesla T4?
- An estimate from memory bandwidth gives about 19 tokens/s at FP16 / BF16.
- Which quantisation of Qwen3.8-4B-Distill 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.