GLM 4.6 Derestricted v3 vs GLM 4.7 Flash Ultimate Irrefusable Heretic
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| GLM 4.6 Derestricted v3 | GLM 4.7 Flash Ultimate Irrefusable Heretic | |
|---|---|---|
| Parameters | 356.8B | 29.9B |
| Context | 203K | 203K |
| Architecture | Glm4MoeForCausalLM | Glm4MoeLiteForCausalLM |
| License | MIT | MIT |
| Downloads | 1.3K | 125 |
| Released | Dec 2025 | Mar 2026 |
VRAM by Quantization: GLM 4.6 Derestricted v3 vs GLM 4.7 Flash Ultimate Irrefusable Heretic
| Quantization | Bits | GLM 4.6 Derestricted v3 VRAM | GLM 4.7 Flash Ultimate Irrefusable Heretic VRAM |
|---|---|---|---|
| Q2_K | 3.40 | — | 13.8 GB |
| Q3_K_M | 3.90 | — | 15.7 GB |
| Q3_K_S | 3.50 | — | 14.2 GB |
| Q4_0 | 4.00 | — | 16.1 GB |
| Q4_K_M | 4.80 | — | 19.1 GB |
| Q5_K_M | 5.70 | — | 22.4 GB |
| Q6_K | 6.60 | — | 25.8 GB |
| Q8_0 | 8.00 | — | 31.0 GB |
Verdict
GLM 4.6 Derestricted v3 is the more widely downloaded of the two.
Frequently Asked Questions
- Which has a longer context window, GLM 4.6 Derestricted v3 or GLM 4.7 Flash Ultimate Irrefusable Heretic?
GLM 4.6 Derestricted v3 supports 202,752 tokens and GLM 4.7 Flash Ultimate Irrefusable Heretic supports 202,752 tokens.
- What is the difference between GLM 4.6 Derestricted v3 and GLM 4.7 Flash Ultimate Irrefusable Heretic?
GLM 4.6 Derestricted v3 is a 356.8B model from ArliAI (GLM family), while GLM 4.7 Flash Ultimate Irrefusable Heretic is a 29.9B model from llmfan46 (GLM family). Compare their VRAM requirements above to see which fits your GPU or Mac.