Qwen1.5 1.8B vs Thinkless 1.5B RL DeepScaleR

Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.

Qwen1.5 1.8B

Alibaba · 1.8B

Chat

Specifications

Qwen1.5 1.8BThinkless 1.5B RL DeepScaleR
Parameters1.8B1.8B
Context33K33K
ArchitectureQwen2ForCausalLMQwen2ForCausalLM
LicenseOtherApache 2.0
Downloads21.5K2.8K
ReleasedApr 2024Jun 2025

VRAM by Quantization: Qwen1.5 1.8B vs Thinkless 1.5B RL DeepScaleR

QuantizationBitsQwen1.5 1.8B VRAMThinkless 1.5B RL DeepScaleR VRAM
BF1616.004.4 GB3.9 GB

Verdict

Thinkless 1.5B RL DeepScaleR needs less VRAM at BF16 (3.9 GB vs 4.4 GB), so it fits on smaller GPUs. Qwen1.5 1.8B is the more widely downloaded of the two.

Frequently Asked Questions

Which needs less VRAM, Qwen1.5 1.8B or Thinkless 1.5B RL DeepScaleR?

At BF16, Qwen1.5 1.8B needs 4.4 GB and Thinkless 1.5B RL DeepScaleR needs 3.9 GB, so Thinkless 1.5B RL DeepScaleR is the lighter option to run locally.

Which has a longer context window, Qwen1.5 1.8B or Thinkless 1.5B RL DeepScaleR?

Qwen1.5 1.8B supports 32,768 tokens and Thinkless 1.5B RL DeepScaleR supports 32,768 tokens.

What is the difference between Qwen1.5 1.8B and Thinkless 1.5B RL DeepScaleR?

Qwen1.5 1.8B is a 1.8B model from Alibaba (Qwen family), while Thinkless 1.5B RL DeepScaleR is a 1.8B model from Vinnnf. Compare their VRAM requirements above to see which fits your GPU or Mac.