image-text-to-text · ♥ 202 · ↓ 258.7K
A 763B-parameter mixture-of-experts model at 1 bit per parameter, with half of its 384 experts per layer removed and the rest quantized, built for code and agentic workflows. 72.1 GB of transformer weights, 1.05 bits per parameter measured against the original model's transformer (see Overview).
This release is a capability-targeted compression of DeepSeek-V4.1-Flash-1017. Half of the routed experts are removed from the model rather than quantized, and the remaining weights keep the per-tensor quantization of the IQ2_XXS build (2.00 bpw).
Excerpt from the model card on Hugging Face ↗.
ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-GGUF was first seen on Hugging Face · Trending models on Nov 4, 2026. Since then it has appeared in 92 checks on 5 different days. Its best position was #24 of 30, reached on Nov 8, 11:42 UTC. It is #25 right now, climbing from #26 to #25 over the last 6 checks.
Position on Hugging Face · Trending models at every check (lower is better).
Best rank per day (UTC).
🔥 as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 8, 14:42 UTC it is #25, climbing from #26 to #25 over the last 6 checks.
#24 on Hugging Face · Trending models, on Nov 8, 11:42 UTC. Trendoday checks this list every 60 minutes.
It was first seen on Nov 4, 2026 and has been on the list on 5 days (92 checks) since.
It is tagged image-text-to-text with gguf on Hugging Face and has 243k downloads under the mit license.