Inkling Small DSpark Preview — Hardware Requirements & GPU Compatibility
Chat
Inkling Small DSpark Preview is a 1.4B-parameter open language model from RadixArk in the Inkling family. It supports a context window of up to 1,048,576 tokens. At Q4_K_M it needs about 1.18 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 · 256K)Best on 24 GB (Q4_K_M · ~555 tok/s · 1M)Macs from 8 GB (Q4_K_M · ~61 tok/s)
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Inkling Small DSpark Preview
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve RadixArk/Inkling-Small-DSpark-Preview --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (10 GB headroom) · Q4_K_M
- Generation speed
- ~503 tok/s
- generation speed
- Cost per 1M output tokens
- $0.068
- per 1M output tokens
How Much VRAM Does Inkling Small DSpark Preview Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.9 GB | 1.6 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 1M context · ~705 tok/s | |
| 1.0 GB | 1.7 GB | 3-bit medium — 3-bit medium quantization | Fits: 1M context · ~642 tok/s | |
| 1.2 GB | 1.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 1M context · ~555 tok/s | |
| 1.3 GB | 2 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 1M context · ~489 tok/s | |
| 1.5 GB | 2.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 1M context · ~440 tok/s | |
| 1.7 GB | 2.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 1M context · ~377 tok/s | |
| 3.1 GB | 3.8 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 512K context · ~209 tok/s |
Selected Q4_K_M
4-bit medium quantization1.5GBat 16K context
- Weights
- 0.8 GB
- KV cache
- 0.3 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 22.5 GB free · ~555 tok/s
≥50 tok/s needs ≥91 GB/s · RTX 5090 ~987, RTX 3090 Ti ~555
Which Hardware Can Run Inkling Small DSpark Preview?
Q4_K_M · 1.2 GBInkling Small DSpark Preview (Q4_K_M) requires 1.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2+ GB is recommended. Using the full 1049K context window can add up to 21.4 GB, bringing total usage to 22.6 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Inkling Small DSpark Preview, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 6.5 GB free · up to 256K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~419Simulate output on RTX 3080RTX 2080 Ti~339Simulate output on RTX 2080 TiRTX 3070 Ti~335Simulate output on RTX 3070 TiM3*8 GB~61Simulate output on iMac 24" M3 (8 GB)Orin Nano~56Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~41Simulate output on iPhone 1720 GB
fits · 18.5 GB free · up to 512K ctx
1 GPU
RX 7900 XT~407Simulate output on RX 7900 XT32–40 GB
fits · 30.5 GB free · up to 1M ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~987Simulate output on RTX 5090M5 Max36 GB~273Simulate output on Mac Studio M5 Max (36 GB)M532 GB~91Simulate output on MacBook Air 13" M5 (32 GB)Orin~113Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~74Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Inkling Small DSpark Preview
Inkling family · 3 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM V 4.6 ThinkingOpenBMB | — | 1.5 GB | ~580 | same size |
| Sweep Next Edit 1.5BXenova | — | 1.6 GB | ~551 | same size |
| Ouro 1.4BByteDance | — | 6.4 GB | ~184 | same size |
| OLMo 2 0425 1B InstructAllen AI | — | 1.7 GB | ~449 | same size |
| Granite 3.0 1B A400m InstructIBM | — | 1.3 GB | ~524 | same size |
| Transformer 1.3B 100Bfla-hub | — | 3 GB | ~218 | same size |
Specifications
- Publisher
- RadixArk
- Family
- Inkling
- Parameters
- 1.4B
- Architecture
- DSparkDraftModel
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 201,024
- Release Date
- 2026-07-30
Frequently Asked Questions
How much VRAM does Inkling Small DSpark Preview need?
Inkling Small DSpark Preview requires 1.2 GB of VRAM at Q4_K_M, or 3.1 GB at BF16. Full 1049K context adds up to 21.4 GB (22.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.4B × 4.8 bits ÷ 8 = 0.8 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 ≈ 21.8 GB (at full 1049K context)
VRAM usage by quantization
What's the best quantization for Inkling Small DSpark Preview?
For Inkling Small DSpark Preview, Q4_K_M (1.2 GB) offers the best balance of quality and VRAM usage. Q5_K_M (1.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.9 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Inkling Small DSpark Preview on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Inkling Small DSpark Preview. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.2 GB of usable unified memory (RAM minus macOS overhead).
Can I run Inkling Small DSpark Preview locally?
Yes — Inkling Small DSpark Preview can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Inkling Small DSpark Preview?
At Q4_K_M, Inkling Small DSpark Preview can reach ~4068 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~555 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 ÷ 1.18 × 0.65 = ~4407 tok/s
Estimated speed at Q4_K_M (1.2 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Inkling Small DSpark Preview?
At Q4_K_M, the download is about 0.84 GB. The full-precision BF16 version is 2.79 GB. The smallest option (Q2_K) is 0.59 GB.
Which GPUs can run Inkling Small DSpark Preview?
52 consumer GPUs can run Inkling Small DSpark Preview 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 Inkling Small DSpark Preview?
163 devices with unified memory can run Inkling Small DSpark Preview at Q4_K_M (1.2 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.