DeepSeek-V4.1-Flash-bf16
Prime Intellect released a bfloat16 re-export of DeepSeek-V4.1-Flash on Hugging Face, 1.34 TB across 48 safetensors shards.
The Deploy Log | Companies | Free, no signup
Every row from Prime Intellect in The Deploy Log: 7 rows, newest first, each linking the publisher's own page. The newest shipped are DeepSeek-V4.1-Flash-bf16 and Qwen3-0.6B-Reverse-Text-SFT-untied. The first is dated and the newest . By lane: Models and APIs 7. They fall in 1 month. The tables below count them by lane, month and platform, and date them.
| Lane | Rows |
|---|---|
| Models and APIs | 7 |
| Figure | Value |
|---|---|
| First row dated | |
| Newest row dated | |
| Median days between release days, publisher's dates only | 5.5 |
| Platform | Rows |
|---|---|
| Hugging Face | 1 |
Prime Intellect released a bfloat16 re-export of DeepSeek-V4.1-Flash on Hugging Face, 1.34 TB across 48 safetensors shards.
Untied copy of Qwen3-0.6B-Reverse-Text-SFT with tie_word_embeddings false for trainers that don't support tied LM heads.
Untied copy of Qwen3-0.6B with tie_word_embeddings false for trainers that don't support tied LM heads.
Untied copy of Qwen3-4B-Instruct-2507 with tie_word_embeddings false, loadable by trainers that don't support tied LM heads.
Untied copy of Qwen3.5-4B with tie_word_embeddings false, loadable by trainers that don't support tied LM heads.
Prime Intellect released Qwen3.5-0.8B-Reverse-Text-RL, a short RL fine-tune for the reverse-text environment.
Prime Intellect released Qwen3.5-0.8B-Reverse-Text-SFT, a short SFT fine-tune of Qwen3.5-0.8B.
One line every time AI actually ships, around the clock, free on Threads and Bluesky. Every one is in The Deploy Log with its source.