h2o-lightning-31b
Side-by-side specs, memory needs, licence, runtimes and benchmarks. Add up to 4 models.
--vram
--gpus
--quant
--add
On your GPU
- h2o-lightning-31b
| Property | |
|---|---|
| Overview | |
| Task | Vision |
| Parameters | 31.3B |
| Active parameters | dense |
| Context length | — |
| Input → output | |
| Released | 20 Oct 2026 |
| Licence | h2o-model-non-commercial-licence-v1.1 |
| Gated download | yes, accept terms |
| Memory and speed | |
| Fits your hardwarepick a GPU above | ≈21 GB |
| VRAM at Q4 | ≈21 GB |
| VRAM at Q8 | ≈35 GB |
| VRAM at FP16 | ≈64 GB |
| Est. generation speedpick a GPU above | — |
| Popularity | |
| Downloads / 30 days | 690 |
| Likes | 8 |
| Runs with | |
| llama.cpp | |
| SGLang | |
| Transformers | |
| vLLM | |
| Ollama tag | — |
| Architecture | |
| Architecture | Gemma4ForConditionalGeneration |
| Weights dtype | bfloat16 |
| GGUF available | no |
Keep comparing
Memory figures are estimates for an 8K context at the chosen quantisation (Q4_K_M for LLMs by default). Speeds are rough, memory-bound estimates. Self-reported benchmark scores come from the model authors.