PrunedHub Qwen3.5 35B A3B 80pct vs Qwen3.5 35B A3B DFlash
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| PrunedHub Qwen3.5 35B A3B 80pct | Qwen3.5 35B A3B DFlash | |
|---|---|---|
| Parameters | 35B | 35B |
| Context | — | 262K |
| Architecture | — | DFlashDraftModel |
| License | Apache 2.0 | MIT |
| Downloads | 578 | 705 |
| Released | Feb 2026 | Mar 2026 |
VRAM by Quantization: PrunedHub Qwen3.5 35B A3B 80pct vs Qwen3.5 35B A3B DFlash
| Quantization | Bits | PrunedHub Qwen3.5 35B A3B 80pct VRAM | Qwen3.5 35B A3B DFlash VRAM |
|---|---|---|---|
| BF16 | 16.00 | 77 GB | 70.3 GB |
| Q2_K | 3.40 | 16.4 GB | 15.2 GB |
| Q3_K_M | 3.90 | 18.8 GB | 17.4 GB |
| Q4_K_M | 4.80 | 23.1 GB | 21.3 GB |
| Q5_K_M | 5.70 | 27.4 GB | 25.3 GB |
| Q6_K | 6.60 | 31.8 GB | 29.2 GB |
| Q8_0 | 8.00 | 38.5 GB | 35.3 GB |
Verdict
Qwen3.5 35B A3B DFlash needs less VRAM at Q4_K_M (21.3 GB vs 23.1 GB), so it fits on smaller GPUs. Qwen3.5 35B A3B DFlash is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, PrunedHub Qwen3.5 35B A3B 80pct or Qwen3.5 35B A3B DFlash?
At Q4_K_M, PrunedHub Qwen3.5 35B A3B 80pct needs 23.1 GB and Qwen3.5 35B A3B DFlash needs 21.3 GB, so Qwen3.5 35B A3B DFlash is the lighter option to run locally.
- What is the difference between PrunedHub Qwen3.5 35B A3B 80pct and Qwen3.5 35B A3B DFlash?
PrunedHub Qwen3.5 35B A3B 80pct is a 35B model from GOBA-AI-Labs (Qwen family), while Qwen3.5 35B A3B DFlash is a 35B model from z-lab (Qwen family). Compare their VRAM requirements above to see which fits your GPU or Mac.