Downloads · 30 days
25
5% of all-time downloads
DeepSeek-R1-Distill-Qwen-1.5B-GGUF-Q4_K_M
MR-CODESPIKE/DeepSeek-R1-Distill-Qwen-1.5B-GGUF-Q4_K_M
DeepSeek-R1-Distill-Qwen-1.5B-GGUF-Q4_K_M is a machine learning model from MR-CODESPIKE. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repository publishes a GGUF-format, Q4KM quantized artifact identified as a DeepSeek-R1-Distill-Qwen 1.5B model. It is intended for local inference through a GGUF-compatible runtime.
All-time downloads
540
Public
Repo size
1.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf1.1 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 13, 2026
- Updated
- Sep 4, 2026
- SHA
- 9b879f1b
Model card
From the Hugging Face model README
DeepSeek-R1-Distill-Qwen 1.5B GGUF — Q4_K_M
This repository publishes a GGUF-format, Q4_K_M quantized artifact identified as a DeepSeek-R1-Distill-Qwen 1.5B model. It is intended for local inference through a GGUF-compatible runtime.
Intended use and limitations
Use it for local research, prompt experiments, and resource-constrained applications. Reasoning-style output can still be incorrect or incomplete; do not treat it as a verified source or use it alone for high-impact decisions. Review the upstream DeepSeek and Qwen licenses and model cards before redistribution.
pip install llama-cpp-python
Load the repository's GGUF file with a llama.cpp-compatible runtime. Use the upstream instruction format and record the runtime, context, sampling, and hardware settings for reproducible comparisons.
Q4_K_M identifies the quantization variant. Its memory and quality characteristics are not equivalent to the original unquantized checkpoint.
- Created
- Jul 13, 2026
- Updated
- Sep 4, 2026