LFM3-VLD-2B-Multipass GGUF
GGUF exports of webbrain-one/lfm3-vld-2b for running in llama.cpp both as a multimodal chat model (/v1/chat/completions) and as a multipass decision model (/v1/systemone) via lfm3.decision.type = "webbrain-vld".
Files
| File | Quantization | Size |
|---|---|---|
LFM3-VLD-2B-BF16.gguf |
BF16 |
3.3 GB |
LFM3-VLD-2B-Q8_0.gguf |
Q8_0 |
1.8 GB |
LFM3-VLD-2B-Q4_K_M.gguf |
Q4_K_M |
1.1 GB |
mmproj-LFM3-VLD-2B-F16.gguf |
Vision Projector (F16) |
362 MB |
Usage with llama-server
llama-server \
-m LFM3-VL-2B-VLD-Q8_0.gguf \
--mmproj mmproj-LFM3-VL-2B-VLD-F16.gguf \
-ngl 99 -c 16384 --port 8080