Spark-X2.5 4B hardware requirements
What is Spark-X2.5 4B?
Spark-X2.5 4B is a compact general-purpose model that the SparkLLM team released in September 2026 alongside a 1.7B version. Its card highlights coding, tool use and agent workflows, more than 200 languages and a native context of up to 1M tokens. Thinking is on by default, the license is Apache 2.0, and it needs llama.cpp b10828 or Ollama 0.34.1 or later.
About the model
- Parameters
- 4.11B
- Attention
- Sliding-window attention
- Max context
- 1,048,576 tokens
- Released
- 2026-08-24
- Model card
- Spark-X2.5 4B on Hugging Face
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| Q4_K_Mbaseline | 2.60 GB | Good balance | Official GGUF · XHToken |
| Q8_0 | 4.38 GB | Near-lossless | Official GGUF · XHToken |
Memory needed by quant and context
| Quant | 4k | 8k | 16k | 32k | 64k | 128k | 256k |
|---|---|---|---|---|---|---|---|
| Q4_K_M | 3.3 | 3.5 | 3.8 | 4.6 | 6.1 | 9.1 | 15.2 |
| Q8_0 | 5.1 | 5.2 | 5.6 | 6.4 | 7.9 | 10.9 | 16.9 |
Which GPUs can run Spark-X2.5 4B?
How to read the verdicts
- Runs great
- Fully on the GPU at 20 tok/s or more
- Runs well
- Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
- Runs slowly
- 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
- Won't run
- Does not fit, or under 2 tok/s
Filter this list by budget, type and context in the calculator
Scroll sideways to see every column.
| Hardware | Verdict | Speed | Quant | Memory | Runs as | Context | Notes | Price |
|---|---|---|---|---|---|---|---|---|
| GeForce RTX 5090 | Runs great | est. 432.3 tok/s380.4–484.1calibrated estimate ±12% | Q4_K_M | 4.1 / 32.0 GB | Full GPU | up to 256k | — | $4,200 street (as of 2026-08-09) |
| Radeon RX 7900 XTX | Runs great | est. 251.4 tok/s221.2–281.6calibrated estimate ±12% | Q4_K_M | 4.1 / 24.0 GB | Full GPU | up to 256k | — | $999 launch MSRP |
| GeForce RTX 3090 Ti | Runs great | est. 243.1 tok/s214.0–272.3calibrated estimate ±12% | Q4_K_M | 4.1 / 24.0 GB | Full GPU | up to 256k | — | $1,999 launch MSRP |
| GeForce RTX 4090 | Runs great | est. 243.1 tok/s214.0–272.3calibrated estimate ±12% | Q4_K_M | 4.1 / 24.0 GB | Full GPU | up to 256k | — | $2,755 street (as of 2026-08-09) |
| Apple M5 Ultra · 96 GB | Runs great | est. 241.2 tok/s193.0–289.4calibrated estimate ±20% | Q4_K_M | 3.5 / 67.2 GB | Unified memory | up to 256k | — | — |
| GeForce RTX 5080 | Runs great | est. 231.6 tok/s203.8–259.4calibrated estimate ±12% | Q4_K_M | 4.1 / 16.0 GB | Full GPU | up to 256k | — | $1,256 street (as of 2026-08-09) |
| GeForce RTX 3090 | Runs great | est. 225.8 tok/s198.7–252.9calibrated estimate ±12% | Q4_K_M | 4.1 / 24.0 GB | Full GPU | up to 256k | — | $1,050 street (as of 2026-08-09) |
| GeForce RTX 3080 12GB | Runs great | est. 220.0 tok/s193.6–246.4calibrated estimate ±12% | Q4_K_M | 4.1 / 12.0 GB | Full GPU | up to 128k | — | $799 launch MSRP |
| GeForce RTX 5070 Ti | Runs great | est. 216.1 tok/s190.2–242.1calibrated estimate ±12% | Q4_K_M | 4.1 / 16.0 GB | Full GPU | up to 256k | — | $949 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Runs great | est. 216.1 tok/s190.2–242.1calibrated estimate ±12% | Q4_K_M | 4.1 / 16.0 GB | Full GPU | up to 256k | — | — |
| GeForce RTX 5090 Laptop | Runs great | est. 216.1 tok/s190.2–242.1calibrated estimate ±12% | Q4_K_M | 4.1 / 24.0 GB | Full GPU | up to 256k | — | — |
| Radeon RX 7900 XT | Runs great | est. 209.5 tok/s184.4–234.7calibrated estimate ±12% | Q4_K_M | 4.1 / 20.0 GB | Full GPU | up to 256k | — | $899 launch MSRP |
| GeForce RTX 3080 10GB | Runs great | est. 183.3 tok/s161.3–205.3calibrated estimate ±12% | Q4_K_M | 4.1 / 10.0 GB | Full GPU | up to 128k | — | $699 launch MSRP |
| GeForce RTX 4080 Super | Runs great | est. 177.5 tok/s156.2–198.8calibrated estimate ±12% | Q4_K_M | 4.1 / 16.0 GB | Full GPU | up to 256k | — | $999 launch MSRP |
| GeForce RTX 4080 | Runs great | est. 173.0 tok/s152.2–193.7calibrated estimate ±12% | Q4_K_M | 4.1 / 16.0 GB | Full GPU | up to 256k | — | $1,199 launch MSRP |
| Radeon RX 9070 | Runs great | est. 168.9 tok/s148.6–189.2calibrated estimate ±12% | Q4_K_M | 4.1 / 16.0 GB | Full GPU | up to 256k | — | $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Runs great | est. 168.9 tok/s148.6–189.2calibrated estimate ±12% | Q4_K_M | 4.1 / 16.0 GB | Full GPU | up to 256k | — | $689 street (as of 2026-08-09) |
| Radeon RX 7800 XT | Runs great | est. 163.4 tok/s143.8–183.0calibrated estimate ±12% | Q4_K_M | 4.1 / 16.0 GB | Full GPU | up to 256k | — | $499 launch MSRP |
| GeForce RTX 4070 Ti Super | Runs great | est. 162.1 tok/s142.6–181.5calibrated estimate ±12% | Q4_K_M | 4.1 / 16.0 GB | Full GPU | up to 256k | — | $799 launch MSRP |
| GeForce RTX 5070 | Runs great | est. 162.1 tok/s142.6–181.5calibrated estimate ±12% | Q4_K_M | 4.1 / 12.0 GB | Full GPU | up to 128k | — | $629 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Runs great | est. 162.1 tok/s142.6–181.5calibrated estimate ±12% | Q4_K_M | 4.1 / 12.0 GB | Full GPU | up to 128k | — | — |
| Apple M3 Ultra · 96 GB | Runs great | est. 160.9 tok/s128.7–193.0calibrated estimate ±20% | Q4_K_M | 3.5 / 67.2 GB | Unified memory | up to 256k | — | — |
| Apple M5 Max (40-core GPU) · 48 GB | Runs great | est. 160.8 tok/s128.6–193.0calibrated estimate ±20% | Q4_K_M | 3.5 / 33.6 GB | Unified memory | up to 256k | — | — |
| Apple M2 Ultra · 64 GB | Runs great | est. 157.1 tok/s125.7–188.6calibrated estimate ±20% | Q4_K_M | 3.5 / 44.8 GB | Unified memory | up to 256k | — | — |
| GeForce RTX 2080 Ti | Runs great | est. 148.6 tok/s130.8–166.4calibrated estimate ±12% | Q4_K_M | 4.1 / 11.0 GB | Full GPU | up to 128k | — | $999 launch MSRP |
| Apple M4 Max (40-core GPU) · 48 GB | Runs great | est. 143.0 tok/s114.4–171.6calibrated estimate ±20% | Q4_K_M | 3.5 / 33.6 GB | Unified memory | up to 256k | — | — |
| GeForce RTX 4090 Laptop | Runs great | est. 138.9 tok/s122.3–155.6calibrated estimate ±12% | Q4_K_M | 4.1 / 16.0 GB | Full GPU | up to 256k | — | — |
| GeForce RTX 4070 | Runs great | est. 121.6 tok/s107.0–136.2calibrated estimate ±12% | Q4_K_M | 4.1 / 12.0 GB | Full GPU | up to 128k | — | $599 launch MSRP |
| GeForce RTX 4070 Super | Runs great | est. 121.6 tok/s107.0–136.2calibrated estimate ±12% | Q4_K_M | 4.1 / 12.0 GB | Full GPU | up to 128k | — | $599 launch MSRP |
| Apple M5 Max (32-core GPU) · 36 GB | Runs great | est. 120.5 tok/s96.4–144.6calibrated estimate ±20% | Q4_K_M | 3.5 / 25.2 GB | Unified memory | up to 128k | — | — |
| GeForce GTX 1080 Ti | Runs great | est. 116.7 tok/s81.7–151.8theoretical estimate ±30% | Q4_K_M | 4.1 / 11.0 GB | Full GPU | up to 128k | — | $699 launch MSRP |
| GeForce RTX 3070 | Runs great | est. 108.1 tok/s95.1–121.0calibrated estimate ±12% | Q4_K_M | 4.1 / 8.0 GB | Full GPU | up to 64k | — | $499 launch MSRP |
| GeForce RTX 5060 | Runs great | est. 108.1 tok/s95.1–121.0calibrated estimate ±12% | Q4_K_M | 4.1 / 8.0 GB | Full GPU | up to 64k | — | $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 16GB | Runs great | est. 108.1 tok/s95.1–121.0calibrated estimate ±12% | Q4_K_M | 4.1 / 16.0 GB | Full GPU | up to 128k | — | $569 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 8GB | Runs great | est. 108.1 tok/s95.1–121.0calibrated estimate ±12% | Q4_K_M | 4.1 / 8.0 GB | Full GPU | up to 64k | — | $429 street (as of 2026-08-09) |
| Apple M4 Max (32-core GPU) · 36 GB | Runs great | est. 107.4 tok/s85.9–128.8calibrated estimate ±20% | Q4_K_M | 3.5 / 25.2 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 4080 Laptop | Runs great | est. 104.2 tok/s91.7–116.7calibrated estimate ±12% | Q4_K_M | 4.1 / 12.0 GB | Full GPU | up to 128k | — | — |
| Intel Arc B580 | Runs great | est. 92.7 tok/s74.2–111.3calibrated estimate ±20% | Q4_K_M | 4.1 / 12.0 GB | Full GPU | up to 128k | — | $290 street (as of 2026-08-09) |
| GeForce RTX 3060 12GB | Runs great | est. 86.8 tok/s76.4–97.3calibrated estimate ±12% | Q4_K_M | 4.1 / 12.0 GB | Full GPU | up to 128k | — | $250 street (as of 2026-08-09) |
| Radeon RX 9060 XT 16GB | Runs great | est. 84.3 tok/s74.2–94.4calibrated estimate ±12% | Q4_K_M | 4.1 / 16.0 GB | Full GPU | up to 128k | — | $449 street (as of 2026-08-09) |
| Apple M5 Pro · 24 GB | Runs great | est. 80.4 tok/s64.3–96.5calibrated estimate ±20% | Q4_K_M | 3.5 / 16.8 GB | Unified memory | up to 128k | — | — |
| NVIDIA DGX Spark · 64 GB | Runs great | est. 73.4 tok/s58.7–88.1calibrated estimate ±20% | Q4_K_M | 3.5 / 48.2 GB | Unified memory | up to 64k | — | $3,999 launch MSRP (128 GB) |
| Ryzen AI Max+ 395 (Strix Halo) · 32 GB | Runs great | est. 72.3 tok/s57.9–86.8calibrated estimate ±20% | Q4_K_M | 3.5 / 22.4 GB | Unified memory | up to 64k | — | $1,999 launch MSRP (128 GB) |
| Apple M4 Pro · 24 GB | Runs great | est. 71.5 tok/s57.2–85.8calibrated estimate ±20% | Q4_K_M | 3.5 / 16.8 GB | Unified memory | up to 64k | — | — |
| GeForce RTX 4060 Ti 16GB | Runs great | est. 69.5 tok/s61.1–77.8calibrated estimate ±12% | Q4_K_M | 4.1 / 16.0 GB | Full GPU | up to 64k | — | $499 launch MSRP |
| GeForce RTX 4060 Ti 8GB | Runs great | est. 69.5 tok/s61.1–77.8calibrated estimate ±12% | Q4_K_M | 4.1 / 8.0 GB | Full GPU | up to 64k | — | $399 launch MSRP |
| GeForce RTX 4060 | Runs great | est. 65.6 tok/s57.7–73.5calibrated estimate ±12% | Q4_K_M | 4.1 / 8.0 GB | Full GPU | up to 64k | — | $299 launch MSRP |
| GeForce RTX 4060 Laptop | Runs great | est. 61.8 tok/s54.3–69.2calibrated estimate ±12% | Q4_K_M | 4.1 / 8.0 GB | Full GPU | up to 64k | — | — |
| GeForce RTX 4070 Laptop | Runs great | est. 61.8 tok/s54.3–69.2calibrated estimate ±12% | Q4_K_M | 4.1 / 8.0 GB | Full GPU | up to 64k | — | — |
| GeForce RTX 3050 8GB | Runs great | est. 54.0 tok/s47.5–60.5calibrated estimate ±12% | Q4_K_M | 4.1 / 8.0 GB | Full GPU | up to 64k | — | $249 launch MSRP |
| Apple M5 · 16 GB | Runs great | est. 40.2 tok/s32.2–48.3calibrated estimate ±20% | Q4_K_M | 3.5 / 11.2 GB | Unified memory | up to 32k | — | — |
| Apple M6 · 16 GB | Runs great | est. 40.2 tok/s32.2–48.3calibrated estimate ±20% | Q4_K_M | 3.5 / 11.2 GB | Unified memory | up to 32k | — | — |
| Apple M4 · 16 GB | Runs great | est. 31.4 tok/s25.1–37.7calibrated estimate ±20% | Q4_K_M | 3.5 / 11.2 GB | Unified memory | up to 8k | — | — |
| DDR5-6000 dual-channel CPU · 16 GB | Runs slowly | est. 16.5 tok/s13.2–19.8calibrated estimate ±20% | Q4_K_M | 2.9 GB RAM | CPU only | up to 128k |
| — |
| DDR5-5600 dual-channel CPU · 16 GB | Runs slowly | est. 15.4 tok/s12.4–18.5calibrated estimate ±20% | Q4_K_M | 2.9 GB RAM | CPU only | up to 128k |
| — |
| DDR4-3200 dual-channel CPU · 16 GB | Runs slowly | est. 8.8 tok/s7.1–10.6calibrated estimate ±20% | Q4_K_M | 2.9 GB RAM | CPU only | up to 128k | — | — |
Models with a thinking mode spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s). With thinking turned off, a model may do one grade better.
Cheapest GPUs that run it
- Runs greatGeForce RTX 3060 12GB$250 street (as of 2026-08-09), est. 86.8 tok/s (76.4–97.3, calibrated estimate ±12%).
Measured results for Spark-X2.5 4B
No public measurements for this model yet.
Frequently asked questions
How much VRAM does Spark-X2.5 4B need?
At Q4_K_M the file is 2.60 GB; with 8k context a graphics card needs about 3.5 GB (weights 2.59 GB, KV cache 0.3 GB, compute buffer 0.6 GB).
What is the cheapest GPU that runs Spark-X2.5 4B well?
Cheapest that runs it great: GeForce RTX 3060 12GB at $250 (street price as of 2026-08-09), est. 86.8 tok/s (76.4–97.3, calibrated estimate ±12%).
Can Spark-X2.5 4B run on an 8 GB, 16 GB or 24 GB GPU?
At Q4_K_M with 8k context: GeForce RTX 4060 — Runs great, est. 65.6 tok/s (57.7–73.5, calibrated estimate ±12%); GeForce RTX 5060 Ti 16GB — Runs great, est. 108.1 tok/s (95.1–121.0, calibrated estimate ±12%); GeForce RTX 3090 — Runs great, est. 225.8 tok/s (198.7–252.9, calibrated estimate ±12%).
Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.