Qwen35 4B Soyuz Merged vs Qwen3.5 4B PTBR
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| Qwen35 4B Soyuz Merged | Qwen3.5 4B PTBR | |
|---|---|---|
| Parameters | 4B | 4B |
| Context | 262K | — |
| Architecture | Qwen3_5ForCausalLM | — |
| License | Apache 2.0 | Apache 2.0 |
| Downloads | 1.2K | 5.8K |
| Released | Jun 2026 | Jun 2026 |
VRAM by Quantization: Qwen35 4B Soyuz Merged vs Qwen3.5 4B PTBR
| Quantization | Bits | Qwen35 4B Soyuz Merged VRAM | Qwen3.5 4B PTBR VRAM |
|---|---|---|---|
| BF16 | 16.00 | 8.5 GB | 8.8 GB |
Verdict
Qwen35 4B Soyuz Merged needs less VRAM at BF16 (8.5 GB vs 8.8 GB), so it fits on smaller GPUs. Qwen3.5 4B PTBR is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, Qwen35 4B Soyuz Merged or Qwen3.5 4B PTBR?
At BF16, Qwen35 4B Soyuz Merged needs 8.5 GB and Qwen3.5 4B PTBR needs 8.8 GB, so Qwen35 4B Soyuz Merged is the lighter option to run locally.
- What is the difference between Qwen35 4B Soyuz Merged and Qwen3.5 4B PTBR?
Qwen35 4B Soyuz Merged is a 4B model from AlexWortega (Qwen family), while Qwen3.5 4B PTBR is a 4B model from lucasmg09 (Qwen family). Compare their VRAM requirements above to see which fits your GPU or Mac.