Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mradermacher/dbrx-instruct-GGUF:Q2_K# Run inference directly in the terminal:
llama cli -hf mradermacher/dbrx-instruct-GGUF:Q2_KUse pre-built binary
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf mradermacher/dbrx-instruct-GGUF:Q2_K# Run inference directly in the terminal:
./llama-cli -hf mradermacher/dbrx-instruct-GGUF:Q2_KBuild from source code
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf mradermacher/dbrx-instruct-GGUF:Q2_K# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/dbrx-instruct-GGUF:Q2_KUse Docker
docker model run hf.co/mradermacher/dbrx-instruct-GGUF:Q2_KAbout
static quants of https://huggingface.co/alpindale/dbrx-instruct
weighted/imatrix quants are available at https://huggingface.co/mradermacher/dbrx-instruct-i1-GGUF
Usage
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | Q2_K | 48.0 | |
| PART 1 PART 2 | IQ3_XS | 53.9 | |
| PART 1 PART 2 | IQ3_S | 56.9 | beats Q3_K* |
| PART 1 PART 2 | Q3_K_S | 56.9 | |
| PART 1 PART 2 | IQ3_M | 58.1 | |
| PART 1 PART 2 | Q3_K_M | 63.2 | lower quality |
| PART 1 PART 2 | Q3_K_L | 68.5 | |
| PART 1 PART 2 | IQ4_XS | 71.0 | |
| PART 1 PART 2 | Q4_K_S | 75.0 | fast, recommended |
| PART 1 PART 2 | Q4_K_M | 80.0 | fast, recommended |
| PART 1 PART 2 | Q5_K_S | 90.7 | |
| PART 1 PART 2 | Q5_K_M | 93.7 | |
| PART 1 PART 2 PART 3 | Q6_K | 108.1 | very good quality |
| PART 1 PART 2 PART 3 | Q8_0 | 139.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.
Thanks
I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.
- Downloads last month
- 33
2-bit
Model tree for mradermacher/dbrx-instruct-GGUF
Base model
alpindale/dbrx-instruct
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf mradermacher/dbrx-instruct-GGUF:Q2_K# Run inference directly in the terminal: llama cli -hf mradermacher/dbrx-instruct-GGUF:Q2_K