Kimi K2 Instruct 0905 vs Kimi K2 Thinking
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| Kimi K2 Instruct 0905 | Kimi K2 Thinking | |
|---|---|---|
| Parameters | 1026.5B | 1058.1B |
| Context | 262K | 262K |
| Architecture | DeepseekV3ForCausalLM | DeepseekV3ForCausalLM |
| License | Other | Other |
| Downloads | 2.7M | 165.0K |
| Released | — | — |
VRAM by Quantization: Kimi K2 Instruct 0905 vs Kimi K2 Thinking
| Quantization | Bits | Kimi K2 Instruct 0905 VRAM | Kimi K2 Thinking VRAM |
|---|---|---|---|
| Q2_K | 3.40 | 440.1 GB | — |
| Q3_K_M | 3.90 | 504.3 GB | — |
| Q3_K_S | 3.50 | 453.0 GB | — |
| Q4_0 | 4.00 | 517.1 GB | — |
| Q4_K_M | 4.80 | 619.8 GB | — |
| Q5_K_M | 5.70 | 735.2 GB | — |
| Q6_K | 6.60 | 850.7 GB | — |
| Q8_0 | 8.00 | 1030.3 GB | — |
Verdict
Kimi K2 Instruct 0905 is the more widely downloaded of the two.
Frequently Asked Questions
- Which has a longer context window, Kimi K2 Instruct 0905 or Kimi K2 Thinking?
Kimi K2 Instruct 0905 supports 262,144 tokens and Kimi K2 Thinking supports 262,144 tokens.
- What is the difference between Kimi K2 Instruct 0905 and Kimi K2 Thinking?
Kimi K2 Instruct 0905 is a 1026.5B model from Moonshot AI (Kimi K2 family), while Kimi K2 Thinking is a 1058.1B model from Moonshot AI (Kimi K2 family). Compare their VRAM requirements above to see which fits your GPU or Mac.