Model catalog

DeepSeek-R1-Distill-Qwen 1.5B

DeepSeek's compact reasoning-focused model distilled from Qwen2.5, adding a smaller option for local reasoning experiments.

Check this model on your hardware See what your PC can run

Model overview

Family: DeepSeek-R1 Distill
Provider: DeepSeek
Architecture: Qwen2
Parameters: 1.5B
Formats: gguf, safetensors
Runtimes: llama.cpp
License: MIT
Maximum context: 131,072 tokens

Available quantizations

Lower-bit quantizations generally use less memory. The compatibility calculator uses these candidates and its transparent approximate memory assumptions; it does not make a performance guarantee.

Q4_K_M

A commonly available lower-memory GGUF variant; the listed memory input is an estimate, not the repository file size.

Bits per weight: 4.5
Source: bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF GGUF repository

Q8_0

A higher-memory GGUF variant where listed by the conversion repository; the listed memory input remains approximate.

Bits per weight: 8
Source: bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF GGUF repository

Compatibility notes

Weight estimates are approximate and include a runtime overhead. Real requirements vary with context length, runtime, drivers, and other system use. A model page cannot determine compatibility without your hardware profile; use the calculator for that assessment.

DeepSeek-R1-Distill-Qwen 1.5B model card; verified value, last verified 2026-09-25. The publisher lists this distilled model under MIT and its config allows up to 131,072 tokens; its model card also notes the Qwen2.5 base-model license. GGUF candidates are tracked separately as a community conversion; runtime and long-context memory requirements are not verified. View source