ggml-org/SmolVLM-256M-Instruct-GGUF

Source: 🤗🏴‍☠️ Rescued by: Alogotronapache-2.0797 MBGGUF✓ 4 checksumsupdated 563d ago

SmolVLM-256M-Instruct

Original model: https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct

For more info, please refer to this PR: https://github.com/ggml-org/llama.cpp/pull/13050

CommentsShare your thoughts and shape the future of sovereign AI.

@ggml-org is unclaimedSign in with the matching Hugging Face account or an organization member account to verify this handle.Claim @ggml-org

Files and sources

SourceAvailable on 🤗

Checksums4 recorded

TorrentFiles match 🤗

Swarm1 seeders reported

Source revision: b9e4379657e1…
Witnessed: 22 Sept 2026, 06:19 UTC
Swarm checked: 14 Nov 2026, 01:45 UTC
Weight files: 4
Model size: 797 MB
Downloads · last month: 28,676
Publisher: Unclaimed

Weights

8-bit

Q8_0175 MB

16-bit

f16328 MB

Family

↑ Quantized from HuggingFaceTB/SmolVLM-256M-Instruct

Speed on real hardware

LocalMaxxing

Output speed for one request at a time, measured by people running this model on their own machines.

2× RTX 3090llama.cpp · Q8_0 · 1 run789 tok/s

LD_LIBRARY_PATH=/home/beta1/qwen38-release/tools/llama-b10442-cuda /home/beta1/qwen38-release/tools/llama-b10442-cuda/llama-bench -m /mnt/pf/pf-deep2/SmolVLM-256M-Instruct-GGUF/SmolVLM-256M-Instruct-Q8_0.gguf -p 512 -n 128 -ngl 99 -fa 1

View run on LocalMaxxing

Median of 1 community runs on 1 setups, from LocalMaxxing.

Run it yourself: setup guide

View provenance entry #7192