Can the Tesla T4 run Raon-1-nano?
Raon-1-nano·3.5B·Tesla T4·16 GB VRAM
Yes. The Tesla T4 runs Raon-1-nano fully in VRAM at FP16 / BF16 (about 9.6 GB of 16 GB), at roughly 25 tokens/s.
- best quant
- FP16 / BF16
- needs
- 9.6 GB
- usable
- 16 GB
- est. speed
- ~25 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Raon-1-nano page →
Every quantisation of Raon-1-nano on the Tesla T4
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 4.6 GB | fits | ~152 tok/s |
| Q3_K_M | 5.2 GB | fits | ~102 tok/s |
| Q4_K_M | 5.5 GB | fits | ~82 tok/s |
| Q5_K_M | 6.0 GB | fits | ~70 tok/s |
| Q6_K | 6.1 GB | fits | ~61 tok/s |
| Q8_0 | 6.8 GB | fits | ~47 tok/s |
| FP16 / BF16 pick | 9.6 GB | fits | ~25 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 Raon-1-nano on the Tesla T4
Using FP16 / BF16, the best fit for Tesla T4.
ollama run hf.co/KRAFTON/Raon-1-nano-gguf:F16 llama-server -hf KRAFTON/Raon-1-nano-gguf:F16Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get KRAFTON/Raon-1-nano-gguf@F16Then load it from the LM Studio app or with `lms load`.
from transformers import pipeline
pipe = pipeline("text-generation", model="KRAFTON/Raon-1-nano", 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 |
|---|---|---|---|---|
| 3.2B | Q8_0 | ≈4.7 GBFits in memory | ~52 tok/s | |
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~41 tok/s | |
| 3.1B | Q8_0 | ≈4.3 GBFits in memory | ~54 tok/s | |
| 3.8B | Q8_0 | ≈5.5 GBFits in memory | ~43 tok/s | |
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~41 tok/s | |
| 3.7B | Q8_0 | ≈4.9 GBFits in memory | ~45 tok/s |
Other GPUs that run Raon-1-nano
Frequently asked questions
- Can the Tesla T4 run Raon-1-nano?
- Yes. The Tesla T4 runs Raon-1-nano fully in VRAM at FP16 / BF16 (about 9.6 GB of 16 GB), at roughly 25 tokens/s.
- How fast does Raon-1-nano run on the Tesla T4?
- An estimate from memory bandwidth gives about 25 tokens/s at FP16 / BF16.
- Which quantisation of Raon-1-nano 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.