GLM 4.7 Flash REAP 23B A3B vs GLM 4.7 Flash Heretic 1.2.0
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| GLM 4.7 Flash REAP 23B A3B | GLM 4.7 Flash Heretic 1.2.0 | |
|---|---|---|
| Parameters | 23.0B | 29.9B |
| Context | 203K | 203K |
| Architecture | Glm4MoeLiteForCausalLM | Glm4MoeLiteForCausalLM |
| License | MIT | MIT |
| Downloads | 542 | 333 |
| Released | Jan 2026 | Feb 2026 |
VRAM by Quantization: GLM 4.7 Flash REAP 23B A3B vs GLM 4.7 Flash Heretic 1.2.0
| Quantization | Bits | GLM 4.7 Flash REAP 23B A3B VRAM | GLM 4.7 Flash Heretic 1.2.0 VRAM |
|---|---|---|---|
| Q2_K | 3.40 | 10.9 GB | 13.8 GB |
| Q3_K_M | 3.90 | 12.3 GB | 15.7 GB |
| Q3_K_S | 3.50 | 11.2 GB | 14.2 GB |
| Q4_0 | 4.00 | 12.6 GB | 16.1 GB |
| Q4_K_M | 4.80 | 14.9 GB | 19.1 GB |
| Q5_K_M | 5.70 | 17.5 GB | 22.4 GB |
| Q6_K | 6.60 | 20.1 GB | 25.8 GB |
| Q8_0 | 8.00 | 24.1 GB | 31.0 GB |
Verdict
GLM 4.7 Flash REAP 23B A3B needs less VRAM at Q4_K_M (14.9 GB vs 19.1 GB), so it fits on smaller GPUs. GLM 4.7 Flash REAP 23B A3B is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, GLM 4.7 Flash REAP 23B A3B or GLM 4.7 Flash Heretic 1.2.0?
At Q4_K_M, GLM 4.7 Flash REAP 23B A3B needs 14.9 GB and GLM 4.7 Flash Heretic 1.2.0 needs 19.1 GB, so GLM 4.7 Flash REAP 23B A3B is the lighter option to run locally.
- Which has a longer context window, GLM 4.7 Flash REAP 23B A3B or GLM 4.7 Flash Heretic 1.2.0?
GLM 4.7 Flash REAP 23B A3B supports 202,752 tokens and GLM 4.7 Flash Heretic 1.2.0 supports 202,752 tokens.
- What is the difference between GLM 4.7 Flash REAP 23B A3B and GLM 4.7 Flash Heretic 1.2.0?
GLM 4.7 Flash REAP 23B A3B is a 23.0B model from Cerebras (GLM family), while GLM 4.7 Flash Heretic 1.2.0 is a 29.9B model from darkc0de (GLM family). Compare their VRAM requirements above to see which fits your GPU or Mac.