arcee-ai/Llama-Spark download history
arcee-ai/Llama-Spark is an 8.0B-parameter text generation model by arcee-ai. In the last 30 days it was downloaded 105 times (27 in the last 7 days), and 17,733 times in total.
It ranks #180,799 on the Hub by monthly downloads and #47,949 among text generation models.
It has 28 likes.
194 models build on Llama-Spark: 140 quantized, 6 fine-tuned, 0 adapters and 48 merges. Together with the original they were downloaded 24,106 times in the last 30 days. See the Llama-Spark galaxy.
Most downloaded derivatives
- QuantFactory/L3.1-Celestial-Stone-2x8B-DPO-GGUF (merge), 983 downloads in 30 days
- QuantFactory/L3.1-Celestial-Stone-2x8B-GGUF (merge), 834 downloads in 30 days
- QuantFactory/L3.1-Storniitova-8B-GGUF (merge), 460 downloads in 30 days
- mradermacher/Llama-Spark-i1-GGUF (quantized), 340 downloads in 30 days
- mradermacher/Llama-Spark-GGUF (quantized), 153 downloads in 30 days
- tensorblock/Llama-Spark-GGUF (quantized), 75 downloads in 30 days
- matrixportalx/Llama-Spark-Q4_0-GGUF (quantized), 35 downloads in 30 days
- matrixportalx/Llama-Spark-Q4_K_M-GGUF (quantized), 35 downloads in 30 days
- matrixportalx/Llama-Spark-Q4_K_S-GGUF (quantized), 34 downloads in 30 days
- v000000/L3.1-Storniitova-8B (merge), 34 downloads in 30 days
- juliensimon/Llama-Spark-fp8 (quantized), 10 downloads in 30 days
Downloads by month
Downloads in the 30 days up to the end of each month, and the change from the month before.
| Month | Downloads | Change |
|---|---|---|
| Up to 2026-11-18 | 105 | -22% |
| October 2026 | 135 | +2% |
| September 2026 | 133 | +108% |
| August 2026 | 64 | +129% |
| July 2026 | 28 | -3% |
| June 2026 | 29 | +45% |
| May 2026 | 20 | -89% |
| April 2026 | 174 | +195% |
| March 2026 | 59 | +59% |
| February 2026 | 37 | -49% |
| January 2026 | 72 | +6% |
| December 2025 | 68 | +5% |
Its busiest 30 days so far ended on 2024-12-09, with 3,076 downloads.
Open arcee-ai/Llama-Spark on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.