Spark X2.5 1.7B Base — Hardware Requirements & GPU Compatibility
Chat
Spark X2.5 1.7B Base is a 1.7B-parameter open language model from XHToken. It supports a context window of up to 1,048,576 tokens. At BF16 it needs about 3.83 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 64K)Best on 24 GB (BF16 · ~171 tok/s · 256K)Macs from 8 GB (BF16 · ~19 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Spark X2.5 1.7B Base
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve XHToken/Spark-X2.5-1.7B-Base --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (7 GB headroom) · BF16
- Generation speed
- ~61 tok/s
- generation speed
- Cost per 1M output tokens
- $0.34
- per 1M output tokens
How Much VRAM Does Spark X2.5 1.7B Base Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3.8 GB | 5.6 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 256K context · ~171 tok/s |
Selected BF16
Brain floating point 164.7GBat 16K context
- Weights
- 3.4 GB
- KV cache
- 0.9 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 19.4 GB free · ~171 tok/s
≥50 tok/s needs ≥294 GB/s · RTX 5090 ~304, RTX 3090 Ti ~171
Which Hardware Can Run Spark X2.5 1.7B Base?
BF16 · 3.8 GBSpark X2.5 1.7B Base (BF16) requires 3.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 5+ GB is recommended. Using the full 1049K context window can add up to 60.0 GB, bringing total usage to 63.8 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Spark X2.5 1.7B Base, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), MacBook Air 13" M3 (8 GB).
≤ 11 GB
≤ 11 GB tier →fits · 3.4 GB free · up to 64K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~129Simulate output on RTX 3080RTX 2080 Ti~105Simulate output on RTX 2080 TiRTX 3070 Ti~103Simulate output on RTX 3070 TiM3*8 GB~19Simulate output on iMac 24" M3 (8 GB)Orin Nano~17Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~13Simulate output on iPhone 1720 GB
fits · 15.3 GB free · up to 256K ctx
1 GPU
RX 7900 XT~125Simulate output on RX 7900 XT32–40 GB
fits · 27.4 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~304Simulate output on RTX 5090M5 Max36 GB~84Simulate output on Mac Studio M5 Max (36 GB)M532 GB~28Simulate output on MacBook Air 13" M5 (32 GB)Orin~35Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~23Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Granite 4.0 1BIBM | — | 2.6 GB | ~452 | same size |
| LFM2 VL 1.6BLiquid AI | — | 1.5 GB | ~496 | same size |
| Qwen 1 8BAlibaba | — | 1.9 GB | ~542 | same size |
| Qwen3 1.7B BaseAlibaba | — | 3.2 GB | ~417 | same size |
| DeepSeek R1 Distill Qwen 1.5BDeepSeek | — | 1.8 GB | ~461 | same size |
| SmolLM2 1.7B InstructHugging Face | — | 2.9 GB | ~379 | same size |
Fine-tunes & variants(1)
Specifications
- Publisher
- XHToken
- Parameters
- 1.7B
- Architecture
- Spark2_5ForCausalLM
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2026-08-28
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Spark X2.5 1.7B Base need?
Spark X2.5 1.7B Base requires 3.8 GB of VRAM at BF16. Full 1049K context adds up to 60.0 GB (63.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.7B × 16 bits ÷ 8 = 3.4 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 60.4 GB (at full 1049K context)
VRAM usage by quantization
Can I run Spark X2.5 1.7B Base on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Spark X2.5 1.7B Base. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 3.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Spark X2.5 1.7B Base locally?
Yes — Spark X2.5 1.7B Base can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Spark X2.5 1.7B Base?
At BF16, Spark X2.5 1.7B Base can reach ~1253 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~171 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 3.83 × 0.65 = ~1358 tok/s
Estimated speed at BF16 (3.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Spark X2.5 1.7B Base?
At BF16, the download is about 3.42 GB.
Which GPUs can run Spark X2.5 1.7B Base?
52 consumer GPUs can run Spark X2.5 1.7B Base at BF16. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Spark X2.5 1.7B Base?
163 devices with unified memory can run Spark X2.5 1.7B Base at BF16 (3.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.