Downloads · 30 days
118
54% of all-time downloads
forge-qwen2.5-coder-1.5b-mongodb-gguf
tarun-11/forge-qwen2.5-coder-1.5b-mongodb-gguf
forge-qwen2.5-coder-1.5b-mongodb-gguf is a text generation model from tarun-11. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
A LoRA fine-tune of Qwen2.5-Coder-1.5B-Instruct, trained for natural-language - PyMongo query generation, fused into the base weights and quantized here as Q4KM GGUF (llama.cpp K-quant) for CPU serving via llama-cpp-p…
All-time downloads
217
Public
Repo size
986 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf986 MB · 100%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Access
- Public
- Created
- Sep 4, 2026
- Updated
- Sep 4, 2026
- SHA
- abe36b1d
Try a prompt
Base models
Model card
From the Hugging Face model README
forge-qwen2.5-coder-1.5b-mongodb-gguf
A LoRA fine-tune of Qwen2.5-Coder-1.5B-Instruct, trained for natural-language
-> PyMongo query generation, fused into the base weights and quantized here
as Q4_K_M GGUF (llama.cpp K-quant) for CPU serving via
llama-cpp-python or Ollama.
A runnable Gradio demo (space/app.py) ships in the project repo, along with the full write-up, benchmark methodology, and results across serving stacks (mlx_lm, Ollama, vLLM-Metal) and quantization levels: https://github.com/tarun1125/forge-slm-serving-benchmark
Not the same quantization implementation as the MLX 4-bit variant used elsewhere in that benchmark (llama.cpp K-quant vs. MLX's own INT4 scheme) — this GGUF is specifically the one portable to non-Apple-Silicon infrastructure.
- Task
- Text Generation
- License
- apache-2.0
- Created
- Sep 4, 2026
- Updated
- Sep 4, 2026