Yes. The Tesla T4 runs LFM3-1.7B fully in VRAM at FP16 / BF16 (about 4.3 GB of 16 GB), at roughly 51 tokens/s.
- best quant
- FP16 / BF16
- needs
- 4.3 GB
- usable
- 16 GB
- est. speed
- ~51 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the LFM3-1.7B page →
Every quantisation of LFM3-1.7B on the Tesla T4
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 1.6 GB | fits | ~310 tok/s |
| Q3_K_M | 1.7 GB | fits | ~208 tok/s |
| Q4_K_M | 1.9 GB | fits | ~168 tok/s |
| Q5_K_M | 2.1 GB | fits | ~143 tok/s |
| Q6_K | 2.3 GB | fits | ~124 tok/s |
| Q8_0 | 2.7 GB | fits | ~96 tok/s |
| FP16 / BF16 pick | 4.3 GB | fits | ~51 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 LFM3-1.7B on the Tesla T4
Using FP16 / BF16, the best fit for Tesla T4.
ollama run lfm3:1.7bThe library build picks its own default quantisation.
ollama run hf.co/LiquidAI/LFM3-1.7B-GGUF:F16 llama-server -hf LiquidAI/LFM3-1.7B-GGUF:F16Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get LiquidAI/LFM3-1.7B-GGUF@F16Then load it from the LM Studio app or with `lms load`.
from transformers import pipeline
pipe = pipeline("text-generation", model="LiquidAI/LFM3-1.7B", 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 |
|---|---|---|---|---|
| 1.5B | Q8_0 | ≈2.6 GBFits in memory | ~107 tok/s | |
| 2B | Q8_0 | ≈3.2 GBFits in memory | ~82 tok/s | |
| 1.2B | Q8_0 | ≈2.0 GBFits in memory | ~134 tok/s | |
| 1B | Q8_0 | ≈1.8 GBFits in memory | ~166 tok/s | |
| 2.5B | Q8_0 | ≈3.5 GBFits in memory | ~66 tok/s | |
| 3.2B | Q8_0 | ≈4.7 GBFits in memory | ~52 tok/s |
Other GPUs that run LFM3-1.7B
Frequently asked questions
- Can the Tesla T4 run LFM3-1.7B?
- Yes. The Tesla T4 runs LFM3-1.7B fully in VRAM at FP16 / BF16 (about 4.3 GB of 16 GB), at roughly 51 tokens/s.
- How fast does LFM3-1.7B run on the Tesla T4?
- An estimate from memory bandwidth gives about 51 tokens/s at FP16 / BF16.
- Which quantisation of LFM3-1.7B 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.