Phi 3.5 MoE Instruct vs Phi 3 Mini 4k Instruct
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| Phi 3.5 MoE Instruct | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Parameters | 41.9B | 3.8B |
| Context | 131K | 4K |
| Architecture | PhiMoEForCausalLM | Phi3ForCausalLM |
| License | MIT | MIT |
| Downloads | 138.1K | 659.9K |
| Released | — | — |
VRAM by Quantization: Phi 3.5 MoE Instruct vs Phi 3 Mini 4k Instruct
| Quantization | Bits | Phi 3.5 MoE Instruct VRAM | Phi 3 Mini 4k Instruct VRAM |
|---|---|---|---|
| Q2_K | 3.40 | — | 2.7 GB |
| Q3_K_M | 3.90 | — | 3.0 GB |
| Q3_K_S | 3.50 | — | 2.8 GB |
| Q4_0 | 4.00 | — | 3.0 GB |
| Q4_K_M | 4.80 | — | 3.4 GB |
| Q5_K_M | 5.70 | — | 3.8 GB |
| Q6_K | 6.60 | — | 4.3 GB |
| Q8_0 | 8.00 | — | 4.9 GB |
Verdict
Phi 3.5 MoE Instruct supports a longer context window (131K tokens). Phi 3 Mini 4k Instruct is the more widely downloaded of the two.
Frequently Asked Questions
- Which has a longer context window, Phi 3.5 MoE Instruct or Phi 3 Mini 4k Instruct?
Phi 3.5 MoE Instruct supports 131,072 tokens and Phi 3 Mini 4k Instruct supports 4,096 tokens.
- What is the difference between Phi 3.5 MoE Instruct and Phi 3 Mini 4k Instruct?
Phi 3.5 MoE Instruct is a 41.9B model from Microsoft (Phi 3 family), while Phi 3 Mini 4k Instruct is a 3.8B model from Microsoft (Phi 3 family). Compare their VRAM requirements above to see which fits your GPU or Mac.