plamo-3-8b-fin-instruct
Side-by-side specs, memory needs, licence, runtimes and benchmarks. Add up to 4 models.
--vram
--gpus
--quant
--add
On your GPU
- plamo-3-8b-fin-instruct
| Property | |
|---|---|
| Overview | |
| Task | Chat |
| Parameters | 8.5B |
| Active parameters | dense |
| Context length | 256K |
| Input → output | |
| Released | 8 Nov 2026 |
| Licence | plamo-community-license |
| Gated download | no |
| Memory and speed | |
| Fits your hardwarepick a GPU above | ≈6.1 GB |
| VRAM at Q4 | ≈6.1 GB |
| VRAM at Q8 | ≈9.9 GB |
| VRAM at FP16 | ≈18 GB |
| Est. generation speedpick a GPU above | — |
| Popularity | |
| Downloads / 30 days | 983 |
| Likes | 10 |
| Runs with | |
| Jan | |
| KoboldCpp | |
| llama.cpp | |
| LM Studio | |
| LocalAI | |
| Ollama | |
| Transformers | |
| vLLM | |
| Ollama tag | — |
| Architecture | |
| Architecture | Plamo3ForCausalLM |
| Layers | 32 |
| Attention / KV heads | 32 / 4 |
| Vocabulary | 107 520 |
| Weights dtype | bfloat16 |
| GGUF available | yes |
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.