NVIDIA-Nemotron-3-Nano-4B-BF16 is a small language model (SLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response.
lumi-4b
ceia-br·Instruct·released 27 Oct 2026
llama-server -hf Mateus-Nery/lumi-4b-GGUF:Q4_K_XLO Overall é a média aritmética simples dessas cinco métricas, com peso igual para cada uma. Nesse recorte, o Lumi-4B ocupa a 2ª posição entre 9 modelos.
How much VRAM does lumi-4b need?
At Q4_K_M lumi-4b needs about 4.2 GB with an 8K context (4.2 GB at Q4, 9.6 GB at full precision). Pick your GPU to see what fits and how fast it runs.
Needs: ≈4.2 GB · Q4_K_M · 8K context — Pick a GPU to check the fit.
Advanced: context 8K · KV cache 16-bit
Smallest GPU for each quant and context (KV cache 16-bit)
| Quantisation | 8K | 16K | 32K | 64K | 128K | 256K |
|---|---|---|---|---|---|---|
| Q3_K_M | ||||||
| Q4_K_M | ||||||
| Q5_K_M | ||||||
| Q6_K | ||||||
| Q8_0 | ||||||
| FP16 |
≤16 GB card24–32 GB48–96 GBmore
| Quantisation | Total |
|---|---|
| Q2_KHeavy lossSmallest, noticeably worse quality | ≈3.1 GB |
| Q3_K_MNoticeable lossSmall, some quality loss | ≈3.7 GB |
| Q4_K_MrecommendedSmall lossRecommended default for local use | ≈4.2 GB |
| Q5_K_MNear-losslessNear-lossless for most tasks | ≈4.6 GB |
| Q6_KNear-losslessPractically lossless | ≈5.7 GB |
| Q8_0LosslessLossless in practice, twice the size of Q4 | ≈5.9 GB |
| FP16 / BF16LosslessFull precision, as released | ≈9.6 GB |
Estimates for 8K tokens of context: weights + KV cache + runtime overhead. Speed assumes memory-bound decoding at your GPU’s bandwidth. Pick a GPU above and the fit column checks every row against it. Weights marked “file” use the real GGUF download size; “est.” rows are computed from the parameter count.
How to pick a quant
Take the biggest quant that fits with room left for context. Q4_K_M is the usual sweet spot. Below Q4 quality drops fast, above Q6 you mostly pay memory for nothing. Big models (70B+, large MoE) tolerate low quants better than small ones.
- LosslessF16, Q8_0
- Near-losslessQ6_K, Q5_K_M
- Small lossQ5_K_S, Q4_K_M, IQ4_NL, IQ4_XS, Q4_K_S
- Noticeable lossQ4_0, Q3_K_L, Q3_K_M, IQ3_M
- Heavy lossIQ3_XXS, Q3_K_S, IQ2_M, Q2_K
Typical quality loss, not measured per model. Tiers come from KL divergence against FP16 on Llama 3 8B: llama.cpp perplexity README: LLaMA 3 8B scoreboard (KLD and ΔPPL vs FP16, Wikitext-2); llama.cpp quantize tool: ΔPPL per quant type @ Llama-3-8B
How much context fits?
At 8K context, Q4_K_M needs ≈4.2 GB(2.2 GB weights + 1.3 GB KV cache + 0.6 GB overhead). Pick a GPU above to see how much context fits.
Weights + overheadKV cache
Can the RTX 4060 run lumi-4b? →
Speed vs quality per quant
Smaller quants run faster and fit in less memory, but lose quality.
Fits in VRAMTight fitCPU offload✕ won't runQuality is typical KL divergence vs FP16, not measured for this model.
Real-world speed of lumi-4b
Tokens per second measured by people running it at home. A GPU shows a median once 3 reports agree on the same setup. Reports far from our estimate wait for a review. Measure yours with llama-bench →
No medians yet. Be one of the first 3 to report a setup.
All reports
Run lumi-4b locally
--quantQ4_K_Mdefault; pick your GPU to tailor itMateus-Nery/lumi-4b-GGUF
llama-server -hf Mateus-Nery/lumi-4b-GGUF:Q4_K_XLDownloads 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.
Quantised versions and downloads
| Repository | Format | Quant | Size |
|---|---|---|---|
| liodon-ai/lumi-4b-FP8 | Safetensors | FP8 | — |
| Mateus-Nery/lumi-4b-GGUF | GGUF | IQ4_XS | 2.4 GB |
| Mateus-Nery/lumi-4b-GGUF | GGUF | Q3_K_XL | 2.7 GB |
| Mateus-Nery/lumi-4b-GGUF | GGUF | Q5_K_S | 3.0 GB |
| Mateus-Nery/lumi-4b-GGUF | GGUF | Q4_K_XL | 3.1 GB |
| Mateus-Nery/lumi-4b-GGUF | GGUF | Q6_K | 3.9 GB |
| Mateus-Nery/lumi-4b-GGUF | GGUF | Q6_K_XL | 4.6 GB |
| Mateus-Nery/lumi-4b-GGUF | GGUF | BF16 | 8.0 GB |
| HyperScale/lumi-4b-GGUF | GGUF | — | — |
About lumi-4b
O Overall é a média aritmética simples dessas cinco métricas, com peso igual para cada uma. Nesse recorte, o Lumi-4B ocupa a 2ª posição entre 9 modelos.
Full model card on Hugging Face →Alternatives to lumi-4b
All alternatives →We introduce the updated version of the Qwen3-4B non-thinking mode, named Qwen3-4B-Instruct-2507, featuring the following key enhancements:
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
Nanbeige4.2-3B is a compact agentic model built on Nanbeige4.2-3B-Base, designed to combine strong agentic behavior with broad reasoning and alignment capabilities. Its Looped Transformer architecture reuses the transformer layers to increase model capacity without adding parameters.
Model Summary: Granite-4.1-3B is a 3B parameter long-context instruct model finetuned from Granite-4.1-3B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.
A little over a month has passed since Spark-X2.5. In the rapidly evolving world of AI agents, that is enough time to rethink, refine, and move the frontier forward.
lumi-4b FAQ
- How much VRAM does lumi-4b need?
- About 4.2 GB at Q4_K_M with an 8K context. Q8_0 needs about 5.9 GB and full precision about 9.6 GB. Longer contexts need more memory for the KV cache.
- Can lumi-4b run on the RTX 4060?
- Yes. It fits at Q8_0 (about 5.9 GB), at an estimated 35 tokens/s. It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.
- Can I use lumi-4b commercially?
- Unclear. It is released under Unknown licence. No licence stated: assume all rights reserved. Check the licence on the model card before using it in a product.
- What is the context length of lumi-4b?
- 262,144 tokens (256K). The full window needs far more memory than an 8K context.
- How do I run lumi-4b with llama.cpp?
- Run llama-server -hf Mateus-Nery/lumi-4b-GGUF:Q4_K_XL. It downloads the GGUF and starts an OpenAI-compatible server.
Rate this model
Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.
0 comments