Can the RTX 4060 run lumi-4b?
lumi-4b·4B·GeForce RTX 4060·8 GB VRAM
Yes. The RTX 4060 runs lumi-4b fully in VRAM at Q8_0 (about 5.9 GB of 8.0 GB), at roughly 35 tokens/s.
- best quant
- Q8_0
- needs
- 5.9 GB
- usable
- 8.0 GB
- est. speed
- ~35 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 4060
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 3.1 GB | fits | ~115 tok/s |
| Q3_K_M | 3.7 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 | 5.7 GB | fits | ~46 tok/s |
| Q8_0 pick | 5.9 GB | fits | ~35 tok/s |
| FP16 / BF16 | 9.6 GB | offload | ~12 tok/s |
Speed is a bandwidth-based estimate for generating text (272 GB/s); prompt processing and long contexts are slower.
Measured speed on the RTX 4060
No community reports for this pair yet.
Report your own speed →Run lumi-4b on the RTX 4060
Using Q6_K, the best fit for RTX 4060.
llama-server -hf Mateus-Nery/lumi-4b-GGUF:Q6_KDownloads 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 4060 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~35 tok/s | |
| 3.2B | Q8_0 | ≈4.7 GBFits in memory | ~44 tok/s | |
| 3.8B | Q8_0 | ≈5.5 GBFits in memory | ~37 tok/s | |
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~35 tok/s | |
| 4.1B | Q8_0 | ≈5.9 GBFits in memory | ~34 tok/s | |
| 3.1B | Q8_0 | ≈4.3 GBFits in memory | ~46 tok/s |
Other GPUs that run lumi-4b
Frequently asked questions
- Can the RTX 4060 run lumi-4b?
- Yes. The RTX 4060 runs lumi-4b fully in VRAM at Q8_0 (about 5.9 GB of 8.0 GB), at roughly 35 tokens/s.
- How fast does lumi-4b run on the RTX 4060?
- An estimate from memory bandwidth gives about 35 tokens/s at Q8_0.
- Which quantisation of lumi-4b should I use on the RTX 4060?
- 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.