Yes. The RTX A4000 runs lumi-4b fully in VRAM at FP16 / BF16 (about 9.6 GB of 16 GB), at roughly 31 tokens/s.
- best quant
- FP16 / BF16
- needs
- 9.6 GB
- usable
- 16 GB
- est. speed
- ~31 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the lumi-4b page →
Every quantisation of lumi-4b on the RTX A4000
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 3.1 GB | fits | ~189 tok/s |
| Q3_K_M | 3.7 GB | fits | ~127 tok/s |
| Q4_K_M | 4.2 GB | fits | ~102 tok/s |
| Q5_K_M | 4.6 GB | fits | ~87 tok/s |
| Q6_K | 5.7 GB | fits | ~75 tok/s |
| Q8_0 | 5.9 GB | fits | ~58 tok/s |
| FP16 / BF16 pick | 9.6 GB | fits | ~31 tok/s |
Speed is a bandwidth-based estimate for generating text (448 GB/s); prompt processing and long contexts are slower.
Measured speed on the RTX A4000
No community reports for this pair yet.
Report your own speed →Run lumi-4b on the RTX A4000
Using FP16 / BF16, the best fit for RTX A4000.
llama-server -hf Mateus-Nery/lumi-4b-GGUF:BF16Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
vllm serve ceia-br/lumi-4b vllm serve liodon-ai/lumi-4b-FP8services:
vllm:
image: vllm/vllm-openai:latest
command: ceia-br/lumi-4b
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 ceia-br/lumi-4b --host 0.0.0.0 --port 30000services:
sglang:
image: lmsysorg/sglang:latest
command: sglang serve ceia-br/lumi-4b --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.
Chat models that fit the RTX A4000 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~58 tok/s | |
| 3.2B | Q8_0 | ≈4.7 GBFits in memory | ~72 tok/s | |
| 3.8B | Q8_0 | ≈5.5 GBFits in memory | ~60 tok/s | |
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~58 tok/s | |
| 4.1B | Q8_0 | ≈5.9 GBFits in memory | ~56 tok/s | |
| 3.1B | Q8_0 | ≈4.3 GBFits in memory | ~75 tok/s |
Other GPUs that run lumi-4b
Frequently asked questions
- Can the RTX A4000 run lumi-4b?
- Yes. The RTX A4000 runs lumi-4b fully in VRAM at FP16 / BF16 (about 9.6 GB of 16 GB), at roughly 31 tokens/s.
- How fast does lumi-4b run on the RTX A4000?
- An estimate from memory bandwidth gives about 31 tokens/s at FP16 / BF16.
- Which quantisation of lumi-4b should I use on the RTX A4000?
- 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.