Will this model run on your hardware?
Can I run Reka Flash 3 locally?
- 21B parameters
- context up to 32K
- licence: apache-2.0
- Weights: RekaAI/reka-flash-3 · GGUF: bartowski/RekaAI_reka-flash-3-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 22.2 GB |
| Q6_K | 18.4 GB |
| Q5_K_M | 15.6 GB |
| Q4_K_M | 13.6 GB |
| Q3_K_M | 10.9 GB |
| Q2_K | 8.6 GB |
Run it locally
ollama run hf.co/bartowski/RekaAI_reka-flash-3-GGUF:Q4_K_M
llama serve -hf bartowski/RekaAI_reka-flash-3-GGUF:Q4_K_M
LM Studio: open bartowski/RekaAI_reka-flash-3-GGUF