GLM 4.5 vs GLM 4.6V
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| GLM 4.5 | GLM 4.6V | |
|---|---|---|
| Parameters | 358.3B | 107.7B |
| Context | 131K | 131K |
| Architecture | Glm4MoeForCausalLM | Glm4vMoeForConditionalGeneration |
| License | MIT | MIT |
| Downloads | 185.5K | 3.7K |
| Released | — | — |
VRAM by Quantization: GLM 4.5 vs GLM 4.6V
| Quantization | Bits | GLM 4.5 VRAM | GLM 4.6V VRAM |
|---|---|---|---|
| Q2_K | 3.40 | 152.9 GB | 46.2 GB |
| Q3_K_M | 3.90 | 175.3 GB | 52.9 GB |
| Q3_K_S | 3.50 | 157.4 GB | 47.5 GB |
| Q4_0 | 4.00 | 179.8 GB | 54.3 GB |
| Q4_K_M | 4.80 | 215.6 GB | 65.1 GB |
| Q5_K_M | 5.70 | 255.9 GB | 77.2 GB |
| Q6_K | 6.60 | 296.3 GB | 89.3 GB |
| Q8_0 | 8.00 | 359.0 GB | 108.1 GB |
Verdict
GLM 4.6V needs less VRAM at Q4_K_M (65.1 GB vs 215.6 GB), so it fits on smaller GPUs. GLM 4.5 is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, GLM 4.5 or GLM 4.6V?
At Q4_K_M, GLM 4.5 needs 215.6 GB and GLM 4.6V needs 65.1 GB, so GLM 4.6V is the lighter option to run locally.
- Which has a longer context window, GLM 4.5 or GLM 4.6V?
GLM 4.5 supports 131,072 tokens and GLM 4.6V supports 131,072 tokens.
- What is the difference between GLM 4.5 and GLM 4.6V?
GLM 4.5 is a 358.3B model from zai-org (GLM family), while GLM 4.6V is a 107.7B model from zai-org (GLM family). Compare their VRAM requirements above to see which fits your GPU or Mac.