PrunedHub Qwen3.5 35B A3B 80pct vs DeepSeek R1 Distill Qwen 14B Abliterated v2
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| PrunedHub Qwen3.5 35B A3B 80pct | DeepSeek R1 Distill Qwen 14B Abliterated v2 | |
|---|---|---|
| Parameters | 35B | 14.8B |
| Context | — | 131K |
| Architecture | — | Qwen2ForCausalLM |
| License | Apache 2.0 | — |
| Downloads | 578 | 361 |
| Released | Feb 2026 | Jul 2025 |
VRAM by Quantization: PrunedHub Qwen3.5 35B A3B 80pct vs DeepSeek R1 Distill Qwen 14B Abliterated v2
| Quantization | Bits | PrunedHub Qwen3.5 35B A3B 80pct VRAM | DeepSeek R1 Distill Qwen 14B Abliterated v2 VRAM |
|---|---|---|---|
| Q2_K | 3.40 | — | 7.0 GB |
| Q3_K_M | 3.90 | — | 7.9 GB |
| Q3_K_S | 3.50 | — | 7.2 GB |
| Q4_0 | 4.00 | — | 8.1 GB |
| Q4_K_M | 4.80 | 23.1 GB | 9.6 GB |
| Q5_K_M | 5.70 | — | 11.2 GB |
| Q6_K | 6.60 | — | 12.9 GB |
| Q8_0 | 8.00 | — | 15.5 GB |
Verdict
DeepSeek R1 Distill Qwen 14B Abliterated v2 needs less VRAM at Q4_K_M (9.6 GB vs 23.1 GB), so it fits on smaller GPUs. PrunedHub Qwen3.5 35B A3B 80pct is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, PrunedHub Qwen3.5 35B A3B 80pct or DeepSeek R1 Distill Qwen 14B Abliterated v2?
At Q4_K_M, PrunedHub Qwen3.5 35B A3B 80pct needs 23.1 GB and DeepSeek R1 Distill Qwen 14B Abliterated v2 needs 9.6 GB, so DeepSeek R1 Distill Qwen 14B Abliterated v2 is the lighter option to run locally.
- What is the difference between PrunedHub Qwen3.5 35B A3B 80pct and DeepSeek R1 Distill Qwen 14B Abliterated v2?
PrunedHub Qwen3.5 35B A3B 80pct is a 35B model from GOBA-AI-Labs (Qwen family), while DeepSeek R1 Distill Qwen 14B Abliterated v2 is a 14.8B model from huihui-ai (Qwen family). Compare their VRAM requirements above to see which fits your GPU or Mac.