GLM 4.5 Air Derestricted vs GLM 5 Abliterated
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| GLM 4.5 Air Derestricted | GLM 5 Abliterated | |
|---|---|---|
| Parameters | 110.5B | 753.9B |
| Context | 131K | 203K |
| Architecture | Glm4MoeForCausalLM | GlmMoeDsaForCausalLM |
| License | MIT | Apache 2.0 |
| Downloads | 172 | 263 |
| Released | Dec 2025 | Feb 2026 |
VRAM by Quantization: GLM 4.5 Air Derestricted vs GLM 5 Abliterated
| Quantization | Bits | GLM 4.5 Air Derestricted VRAM | GLM 5 Abliterated VRAM |
|---|---|---|---|
| Q2_K | 3.40 | 47.4 GB | 324.6 GB |
| Q3_K_M | 3.90 | 54.3 GB | 371.7 GB |
| Q3_K_S | 3.50 | 48.8 GB | 334.0 GB |
| Q4_0 | 4.00 | 55.7 GB | 381.2 GB |
| Q4_K_M | 4.80 | 66.7 GB | 456.5 GB |
| Q5_K_M | 5.70 | 79.1 GB | 541.4 GB |
| Q6_K | 6.60 | 91.6 GB | 626.2 GB |
| Q8_0 | 8.00 | 110.9 GB | 758.1 GB |
Verdict
GLM 4.5 Air Derestricted needs less VRAM at Q4_K_M (66.7 GB vs 456.5 GB), so it fits on smaller GPUs. GLM 5 Abliterated supports a longer context window (203K tokens). GLM 5 Abliterated is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, GLM 4.5 Air Derestricted or GLM 5 Abliterated?
At Q4_K_M, GLM 4.5 Air Derestricted needs 66.7 GB and GLM 5 Abliterated needs 456.5 GB, so GLM 4.5 Air Derestricted is the lighter option to run locally.
- Which has a longer context window, GLM 4.5 Air Derestricted or GLM 5 Abliterated?
GLM 4.5 Air Derestricted supports 131,072 tokens and GLM 5 Abliterated supports 202,752 tokens.
- What is the difference between GLM 4.5 Air Derestricted and GLM 5 Abliterated?
GLM 4.5 Air Derestricted is a 110.5B model from ArliAI (GLM family), while GLM 5 Abliterated is a 753.9B model from skyblanket (GLM family). Compare their VRAM requirements above to see which fits your GPU or Mac.