README
π₯
2
AI & ML interests
SparkLLM focuses on developing leading general-purpose foundation models and professional AI agent products. The company offers its proprietary Spark model family, together with two companion harness systems, AStudio and Loomy. These products support model access, professional-grade execution of complex tasks, software development and everyday work.
Recent Activity
View all activity
How Can We Submit the 1.7B and 4B Models to the AA Leaderboard?
π 6
1
#22 opened 28 days ago
by 
Tylerwtzhang3
Why such hype around Spark X2.5 4B?
1
#9 opened 20 days ago
by 
the8leggedfriend
dongjiang1989Β
updated a
Space 21 days ago
Amazing little model! I got some proposed chat template fixes
π 6
1
#24 opened 27 days ago
by 
peculiar-ragdoll
Ollama model error
2
#1 opened about 1 month ago
by 
johnlockejrr
How Can We Submit the 1.7B and 4B Models to the AA Leaderboard?
π 6
1
#22 opened 28 days ago
by Tylerwtzhang3
dongjiang1989Β
updated 2
models 28 days ago
θΏεΊ¦ζθζεζ³θ§£ε³ε
2
#5 opened about 1 month ago
by 
KXXS
lyang01Β
updated 4
models about 1 month ago
XHToken/Spark-X2.5-1.7B-GGUF
Text Generation β’ 2B β’ Updated β’ 244k β’ 55
XHToken/Spark-X2.5-4B-GGUF
Text Generation β’ 4B β’ Updated β’ 440k β’ 280
XHToken/Spark-X2.5-1.7B
Text Generation β’ 2B β’ Updated β’ 4.44k β’ 152
XHToken/Spark-X2.5-4B
Text Generation β’ 4B β’ Updated β’ 38.3k β’ 1.42k
dongjiang1989Β
updated a
model about 1 month ago
Request: Build Compatible llama.cpp Runtime for Spark-X2.5-4B-GGUF (Windows, CUDA)
8
#2 opened about 1 month ago
by 
KiberAndy
LM Studio: "unknown model architecture: 'spark2_5'" after following build instructions
2
#3 opened about 1 month ago
by 
MasterLooser
We don't need BF16 GGUF, we need Q8 or Q4 quant weight
π 9
4
#1 opened about 2 months ago
by 
weicj
Turn off thinking mode
1
#1 opened about 1 month ago
by 
Techlogic
Benchmark against Nanbeige 4.2 3B and/or Agents A1 4B?
π 7
8
#2 opened about 2 months ago
by 
EnderOLED
Spark-X2.5 Speed Benchmark
β€οΈπ 3
#9 opened about 1 month ago
by 
pengwenzhi