peculiar-ragdoll
Sharp Spark X2.5 4B
Sharp Spark X2.5 4B is a 4.11B dense spark2_5 model from peculiar-ragdoll. Configured context length is 1,048,576 tokens. License: apache-2.0. Quant sizes are the GGUF file bytes published on Hugging Face when a file exists.
Parameters4.1B
Context1024K
Attentionhybrid
Licenseapache-2.0
36 layers · 4 KV heads · head dim 256 · 27 sliding layers · GGUF repo · config
Quant file sizes
| Quant | File size | Source |
|---|---|---|
| Q6_K | 3.36 GB | Hugging Face file bytes |
On common machines
| Device | Verdict | Quant | Speed |
|---|---|---|---|
| GeForce RTX 4060 Ti 8GB | Runs great | Q6_K | 33–45 |
| GeForce RTX 3060 12GB | Runs great | Q6_K | 41–56 |
| GeForce RTX 4060 Ti 16GB | Runs great | Q6_K | 33–45 |
| GeForce RTX 4090 | Runs great | Q6_K | 115–157 |
| GeForce RTX 5090 | Runs great | Q6_K | 204–279 |
| Apple M4 Pro | Runs great | Q6_K | 31–42 |
| Apple M5 | Runs great | Q6_K | 17–24 |
| CPU only · DDR5-5600 | Runs on CPU | Q6_K | 10–14 |
Smallest devices that fit it fully
- GeForce RTX 3050 6GB — Runs, Q6_K, 19–26 tok/s
- GeForce RTX 2060 6GB — Runs, Q6_K, 38–52 tok/s
- GeForce GTX 1660 Super — Runs, Q6_K, 38–52 tok/s
- GeForce GTX 1660 Ti — Runs, Q6_K, 33–45 tok/s
- Intel Arc A380 — Runs, Q6_K, 21–29 tok/s
- GeForce RTX 5060 Ti 8GB — Runs great, Q6_K, 51–70 tok/s
Run it
Commands for the GeForce RTX 4060 Ti 16GB estimate (Q6_K).
llama.cpp
llama-server -hf peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF:Q6_K -c 8192 -ngl 36
No matching name in the Ollama library snapshot.
LM Studio
lms get peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF # Then load quant Q6_K