inclusionAI Releases GGUF Builds of SingVL S1 4B
Start here
inclusionAI has released GGUF quantized versions of Sing VL S1, a 4B-parameter multimodal decision model built on Qwen3.5, enabling CPU inference through llama.cpp. The release ships three decoder variants — BF16 (8.42 GB), Q8_0 (4.48 GB) and Q4_K_M (2.71 GB) — alongside a shared F16 vision projector, with a default context of 4096 tokens that includes image tokens. The included backend runs on Linux x86_64 CPU. Validation so far covers 9 examples and 11 questions across the three variants. Full public scores for the GGUF builds are still pending, so the quantized versions' benchmark performance has not yet been published.
Generated from reports · updated 11 h ago
Report timeline
Follow the reports to see the event from different sides.
- inclusionAI ModelsSingVL-4B GGUF Released: GGUF Build of Sing VL S1 4B Multimodal Decision Model on Qwen3.5
Sing VL S1, a 4B-parameter multimodal decision model built on Qwen3.5, now has a GGUF release for llama.cpp CPU inference. It ships in BF16 (8.42 GB), Q8_0 (4.48 GB) and Q4_K_M (2.71 GB) decoders plus a shared F16 vision projector, with a default 4096-token context. GGUF validation covers 9 examples and 11 questions; full public scores for the GGUF variants are still pending.
Heat for this event
Not enough continuous observations yet to draw a trend.