GLM 4.6 Derestricted v3 vs GLM 4.7 Flash REAP 23B A3B
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| GLM 4.6 Derestricted v3 | GLM 4.7 Flash REAP 23B A3B | |
|---|---|---|
| Parameters | 356.8B | 23.0B |
| Context | 203K | 203K |
| Architecture | Glm4MoeForCausalLM | Glm4MoeLiteForCausalLM |
| License | MIT | MIT |
| Downloads | 1.3K | 542 |
| Released | Dec 2025 | Jan 2026 |
VRAM by Quantization: GLM 4.6 Derestricted v3 vs GLM 4.7 Flash REAP 23B A3B
| Quantization | Bits | GLM 4.6 Derestricted v3 VRAM | GLM 4.7 Flash REAP 23B A3B VRAM |
|---|---|---|---|
| Q2_K | 3.40 | — | 10.9 GB |
| Q3_K_M | 3.90 | — | 12.3 GB |
| Q3_K_S | 3.50 | — | 11.2 GB |
| Q4_0 | 4.00 | — | 12.6 GB |
| Q4_K_M | 4.80 | — | 14.9 GB |
| Q5_K_M | 5.70 | — | 17.5 GB |
| Q6_K | 6.60 | — | 20.1 GB |
| Q8_0 | 8.00 | — | 24.1 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 REAP 23B A3B?
GLM 4.6 Derestricted v3 supports 202,752 tokens and GLM 4.7 Flash REAP 23B A3B supports 202,752 tokens.
- What is the difference between GLM 4.6 Derestricted v3 and GLM 4.7 Flash REAP 23B A3B?
GLM 4.6 Derestricted v3 is a 356.8B model from ArliAI (GLM family), while GLM 4.7 Flash REAP 23B A3B is a 23.0B model from Cerebras (GLM family). Compare their VRAM requirements above to see which fits your GPU or Mac.