GLM 4.5 Air Derestricted vs GLM 4.6 Derestricted v3
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| GLM 4.5 Air Derestricted | GLM 4.6 Derestricted v3 | |
|---|---|---|
| Parameters | 110.5B | 356.8B |
| Context | 131K | 203K |
| Architecture | Glm4MoeForCausalLM | Glm4MoeForCausalLM |
| License | MIT | MIT |
| Downloads | 172 | 1.3K |
| Released | Dec 2025 | Dec 2025 |
VRAM by Quantization: GLM 4.5 Air Derestricted vs GLM 4.6 Derestricted v3
| Quantization | Bits | GLM 4.5 Air Derestricted VRAM | GLM 4.6 Derestricted v3 VRAM |
|---|---|---|---|
| Q2_K | 3.40 | 47.4 GB | — |
| Q3_K_M | 3.90 | 54.3 GB | — |
| Q3_K_S | 3.50 | 48.8 GB | — |
| Q4_0 | 4.00 | 55.7 GB | — |
| Q4_K_M | 4.80 | 66.7 GB | — |
| Q5_K_M | 5.70 | 79.1 GB | — |
| Q6_K | 6.60 | 91.6 GB | — |
| Q8_0 | 8.00 | 110.9 GB | — |
Verdict
GLM 4.6 Derestricted v3 supports a longer context window (203K tokens). GLM 4.6 Derestricted v3 is the more widely downloaded of the two.
Frequently Asked Questions
- Which has a longer context window, GLM 4.5 Air Derestricted or GLM 4.6 Derestricted v3?
GLM 4.5 Air Derestricted supports 131,072 tokens and GLM 4.6 Derestricted v3 supports 202,752 tokens.
- What is the difference between GLM 4.5 Air Derestricted and GLM 4.6 Derestricted v3?
GLM 4.5 Air Derestricted is a 110.5B model from ArliAI (GLM family), while GLM 4.6 Derestricted v3 is a 356.8B model from ArliAI (GLM family). Compare their VRAM requirements above to see which fits your GPU or Mac.