Spark X2.5 4B Base — Hardware Requirements & GPU Compatibility
Chat
Spark X2.5 4B Base is a 4.1B-parameter open language model from XHToken. It supports a context window of up to 1,048,576 tokens. At Q4_K_M it needs about 2.96 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 32K)Best on 24 GB (Q4_K_M · ~221 tok/s · 128K)Macs from 8 GB (Q4_K_M · ~24 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Spark X2.5 4B Base
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve XHToken/Spark-X2.5-4B-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) · Q4_K_M
- Generation speed
- ~79 tok/s
- generation speed
- Cost per 1M output tokens
- $0.27
- per 1M output tokens
How Much VRAM Does Spark X2.5 4B Base Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.2 GB | 5.1 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~293 tok/s | |
| 2.5 GB | 5.3 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~263 tok/s | |
| 3.0 GB | 5.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~221 tok/s | |
| 3.4 GB | 6.3 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~192 tok/s | |
| 3.9 GB | 6.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~169 tok/s | |
| 4.6 GB | 7.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~142 tok/s | |
| 8.7 GB | 11.5 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 128K context · ~75 tok/s |
Selected Q4_K_M
4-bit medium quantization4.3GBat 16K context
- Weights
- 2.5 GB
- KV cache
- 1.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 19.7 GB free · ~221 tok/s
≥50 tok/s needs ≥227 GB/s · RTX 5090 ~394, RTX 3090 Ti ~221
Which Hardware Can Run Spark X2.5 4B Base?
Q4_K_M · 3.0 GBSpark X2.5 4B Base (Q4_K_M) requires 3.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. Using the full 1049K context window can add up to 96.4 GB, bringing total usage to 99.4 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 4B Base, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 3.7 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~167Simulate output on RTX 3080RTX 2080 Ti~135Simulate output on RTX 2080 TiRTX 3070 Ti~134Simulate output on RTX 3070 TiM3*8 GB~24Simulate output on iMac 24" M3 (8 GB)Orin Nano~22Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~16Simulate output on iPhone 1720 GB
fits · 15.7 GB free · up to 128K ctx
1 GPU
RX 7900 XT~162Simulate output on RX 7900 XT32–40 GB
fits · 27.7 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~394Simulate output on RTX 5090M5 Max36 GB~109Simulate output on Mac Studio M5 Max (36 GB)M532 GB~36Simulate output on MacBook Air 13" M5 (32 GB)Orin~45Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~30Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Gemma 3 4B ITGoogle | 64.0 | 5 GB | ~231 | same size |
| Granite Vision 4.1 4BIBM | — | 4 GB | ~228 | same size |
| Qwen3 VL 4B InstructAlibaba | — | 4.5 GB | ~208 | same size |
| MiniCPM V 4OpenBMB | — | 3.1 GB | ~236 | same size |
| Phi 4 Mini ReasoningMicrosoft | — | 4.8 GB | ~228 | same size |
| Phi 3.5 Vision InstructMicrosoft | — | 9.2 GB | ~183 | same size |
Fine-tunes & variants(1)
Specifications
- Publisher
- XHToken
- Parameters
- 4.1B
- 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 4B Base need?
Spark X2.5 4B Base requires 3.0 GB of VRAM at Q4_K_M, or 8.7 GB at BF16. Full 1049K context adds up to 96.4 GB (99.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 4.1B × 4.8 bits ÷ 8 = 2.5 GB
KV Cache + Overhead ≈ 0.5 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 ≈ 96.9 GB (at full 1049K context)
VRAM usage by quantization
What's the best quantization for Spark X2.5 4B Base?
For Spark X2.5 4B Base, Q4_K_M (3.0 GB) offers the best balance of quality and VRAM usage. Q5_K_M (3.4 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 2.2 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Spark X2.5 4B Base on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Spark X2.5 4B Base. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 3.0 GB of usable unified memory (RAM minus macOS overhead).
Can I run Spark X2.5 4B Base locally?
Yes — Spark X2.5 4B Base can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Spark X2.5 4B Base?
At Q4_K_M, Spark X2.5 4B Base can reach ~1622 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~221 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 ÷ 2.96 × 0.65 = ~1757 tok/s
Estimated speed at Q4_K_M (3.0 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 4B Base?
At Q4_K_M, the download is about 2.47 GB. The full-precision BF16 version is 8.22 GB. The smallest option (Q2_K) is 1.75 GB.
Which GPUs can run Spark X2.5 4B Base?
52 consumer GPUs can run Spark X2.5 4B Base at Q4_K_M. 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 4B Base?
163 devices with unified memory can run Spark X2.5 4B Base at Q4_K_M (3.0 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.