SmolLM2-135M-Instruct — GGUF (Q4_K_M)
Unsloth's Q4_K_M GGUF, re-hosted with measured performance for the 1bit engine on Strix Halo. The smallest model in this collection.
Contents
SmolLM2-135M-Instruct-Q4_K_M.gguf
Measured performance (Strix Halo, Vulkan)
pp512: 30637 tok/s · tg128: 562 tok/s
Running it
1bit serve -m SmolLM2-135M-Instruct-Q4_K_M.gguf --device vulkan
Attribution
- Model: HuggingFaceTB/SmolLM2-135M-Instruct, Apache 2.0.
- Quantization: unsloth/SmolLM2-135M-Instruct-GGUF.
- License: Apache 2.0, inherited from the base model.
- Downloads last month
- 65
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for 1bit-MONSTER/SmolLM2-135M-Instruct-GGUF
Base model
HuggingFaceTB/SmolLM2-135M Quantized
HuggingFaceTB/SmolLM2-135M-Instruct