AFM 4.5B vs Goedel Prover v2 32B
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| AFM 4.5B | Goedel Prover v2 32B | |
|---|---|---|
| Parameters | 4.6B | 32.8B |
| Context | 66K | 41K |
| Architecture | ArceeForCausalLM | Qwen3ForCausalLM |
| License | Apache 2.0 | Apache 2.0 |
| Downloads | 1.5K | 7.2K |
| Released | Sep 2025 | Aug 2025 |
VRAM by Quantization: AFM 4.5B vs Goedel Prover v2 32B
| Quantization | Bits | AFM 4.5B VRAM | Goedel Prover v2 32B VRAM |
|---|---|---|---|
| BF16 | 16.00 | 9.7 GB | 66.2 GB |
Verdict
AFM 4.5B needs less VRAM at BF16 (9.7 GB vs 66.2 GB), so it fits on smaller GPUs. AFM 4.5B supports a longer context window (66K tokens). Goedel Prover v2 32B is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, AFM 4.5B or Goedel Prover v2 32B?
At BF16, AFM 4.5B needs 9.7 GB and Goedel Prover v2 32B needs 66.2 GB, so AFM 4.5B is the lighter option to run locally.
- Which has a longer context window, AFM 4.5B or Goedel Prover v2 32B?
AFM 4.5B supports 65,536 tokens and Goedel Prover v2 32B supports 40,960 tokens.
- What is the difference between AFM 4.5B and Goedel Prover v2 32B?
AFM 4.5B is a 4.6B model from Arcee AI, while Goedel Prover v2 32B is a 32.8B model from Goedel-LM. Compare their VRAM requirements above to see which fits your GPU or Mac.