Dolphin 2.9.1 Yi 1.5 34B vs MediPhi Instruct
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| Dolphin 2.9.1 Yi 1.5 34B | MediPhi Instruct | |
|---|---|---|
| Parameters | 34.4B | 3.8B |
| Context | 8K | 131K |
| Architecture | LlamaForCausalLM | Phi3ForCausalLM |
| License | Apache 2.0 | MIT |
| Downloads | 4.7M | 1.9K |
| Released | Sep 2025 | Dec 2025 |
VRAM by Quantization: Dolphin 2.9.1 Yi 1.5 34B vs MediPhi Instruct
| Quantization | Bits | Dolphin 2.9.1 Yi 1.5 34B VRAM | MediPhi Instruct VRAM |
|---|---|---|---|
| BF16 | 16.00 | 69.6 GB | 8.8 GB |
Verdict
MediPhi Instruct needs less VRAM at BF16 (8.8 GB vs 69.6 GB), so it fits on smaller GPUs. MediPhi Instruct supports a longer context window (131K tokens). Dolphin 2.9.1 Yi 1.5 34B is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, Dolphin 2.9.1 Yi 1.5 34B or MediPhi Instruct?
At BF16, Dolphin 2.9.1 Yi 1.5 34B needs 69.6 GB and MediPhi Instruct needs 8.8 GB, so MediPhi Instruct is the lighter option to run locally.
- Which has a longer context window, Dolphin 2.9.1 Yi 1.5 34B or MediPhi Instruct?
Dolphin 2.9.1 Yi 1.5 34B supports 8,192 tokens and MediPhi Instruct supports 131,072 tokens.
- What is the difference between Dolphin 2.9.1 Yi 1.5 34B and MediPhi Instruct?
Dolphin 2.9.1 Yi 1.5 34B is a 34.4B model from dphn (Phi family), while MediPhi Instruct is a 3.8B model from Microsoft (Phi family). Compare their VRAM requirements above to see which fits your GPU or Mac.