Can I run Spark-X2.6-4B on an RTX 4090?
Key facts
Yes. Spark-X2.6-4B runs on an RTX 4090, about 251 tokens per second (tok/s).
It needs about 3.8 GB at standard quality (estimate). Checked . bartowski Q4_K_M GGUF.
The cheapest graphics card on our list that holds it at Q4 is the GeForce RTX 3060 12GB. On an RTX 4090, at 32,768 tokens of context, it still fits in graphics memory (estimate).
Updated · Spark-X2.6-4B on every card
How much memory it needs
It uses about 16% of the memory that is free on this card.
Get a 1-line alert when a faster quant for Spark-X2.6-4B drops — or when GPUs that run it drop >10%
Get a 1-line alert when a new open-weight model fits 8 GB VRAM (3.8 GB at Q4 for Spark-X2.6-4B) or when used RTX 3090 / 4090 & Mac Studio prices drop >10% — weekly, zero spam.
What an RTX 4090 costs
GeForce RTX 4090 24GB$2,446€2,185used (median of sold listings)
EU shops · Shown to visitors in Europe.US shops · Shown to visitors outside Europe.
We never pass off an estimate as a benchmark. Commissions never change which hardware we recommend. How we calculate
Price details
$2,446€2,185
How we priced this
Used price, the typical price of second-hand cards that actually sold.
Source: pcprice.watch, checked 16 Oct 2026.
New (lowest listed in the EU, stock not confirmed): $3,507€3,790 at GPU PRIX, 21 Oct 2026. The page's current low: a ZOTAC Gaming RTX 4090 Trinity OC at amazon.nl and amazon.es (page updated 21 Oct 2026). Boards clearly marked in stock started at €3,990.
Used median €2,185 (typical €2,074–€2,290) from 111 cards sold second-hand, recorded 16 Oct 2026. Not an EU shop price.
Prices excl. shipping unless marked. Euro prices incl. VAT where the seller charges it. Dollar prices are converted from our euro prices without the 21% EU VAT, before US sales tax.
The cheapest graphics card on our list that also runs it (it still needs the rest of a PC): GeForce RTX 3060 12GB, $292€261, used (median of sold listings). Fast~93 tok/s
The cheapest complete machine that runs it: Mac mini M4 16GB, about $615€549 (used). Comfortable~19.3 tok/s
If you buy through these links we may earn a commission. It doesn't change our ranking. How shop links work
As an Amazon Associate I earn from qualifying purchases.
Als Amazon-Partner verdiene ich an qualifizierten Verkäufen.
Als Amazon-Partner verdien ik aan in aanmerking komende aankopen.
Spark-X2.6-4B on other graphics cards
Runs well10
The whole model fits in the graphics memory.
More about the model itself, what it is good at and its licence: Spark-X2.6-4B.
The numbers behind this answer
A model comes in several sizes. Q4 is the standard one most people use; the bigger ones answer a little better but need more memory. Each row adds up the model file, the memory a conversation takes, and some working space, and compares the total with what is free on this card.
Swipe the table sideways to see every column.
| Quality | Conversation | Result | Speed | Model file | Conversation memory | Working space | Total needed | Free memory |
|---|---|---|---|---|---|---|---|---|
| Q4 · standard (smallest that keeps quality) | ~12 pages8,192 tokens | Runs | Fast~251 tok/s | 2.6 GBmeasured file | 0.4 GB | 0.8 GB | 3.8 GB | 23.4 GB |
| Q5 · a bit sharper, a bit bigger | ~12 pages8,192 tokens | Runs | Fast~229 tok/s | 2.9 GB | 0.4 GB | 0.8 GB | 4.1 GB | 23.4 GB |
| Q8 · near full quality, almost twice Q4 | ~12 pages8,192 tokens | Runs | Fast~160 tok/s | 4.4 GB | 0.4 GB | 0.8 GB | 5.6 GB | 23.4 GB |
| FP16 · full quality, over three times Q4 | ~12 pages8,192 tokens | Runs | Fast~90 tok/s | 8.2 GB | 0.4 GB | 0.8 GB | 9.4 GB | 23.4 GB |
| Q4 · standard, longer conversation | ~49 pages32,768 tokens | Runs | Fast~195 tok/s | 2.6 GBmeasured file | 1.3 GB | 0.8 GB | 4.7 GB | 23.4 GB |
Sources and method
Memory and speed on this page are our estimate, not a measured test. Checked . bartowski Q4_K_M GGUF.
Dense text model, 4.11B parameters. Hugging Face safetensors metadata lists 4,112,079,360 parameters, all BF16. 4.11B is that count to two decimals, so our parameter count is an estimate. Architecture Spark2_5ForCausalLM (model type spark2_5): 36 layers, 27 sliding-window layers with a 512-token window and 9 full-attention layers, 4 KV heads, head dim 256, max context 1,048,576. At 8,192 tokens our estimate adds 0.36 GB of conversation memory across that 1,048,576-token max context, plus 0.80 GB of working space. Bartowski's Q4_K_M measured 2.62 GB on 27 Oct 2026 (2,621,104,768 bytes), so the total at 8,192 tokens is 3.78 GB. XHToken's official Q4_K_M measured 3.54 GB on the same day (3,543,441,312 bytes), so that file's total at 8,192 tokens is 4.70 GB. The bartowski file is the one this page uses for the standard total. Apache-2.0. Other runtimes (not llama.cpp). Spark2_5ForCausalLM (spark2_5) runs out of the box via GGUF in llama.cpp, Ollama and LM Studio. Stock vLLM and Transformers releases need custom model registration.
Measured Spark-X2.6-4B on an RTX 4090 yourself? Send us your llama-bench result.
Questions
- Can I run Spark-X2.6-4B on an RTX 4090?
- Yes. Spark-X2.6-4B runs on an RTX 4090, about 251 tokens per second (tok/s).
- How much memory does Spark-X2.6-4B need?
- About 3.8 GB at the standard quality (Q4) for a conversation of up to about 12 pages of text (8,192 tokens), by our estimate: 2.6 GB for the model file (measured), 0.4 GB to hold the conversation and 0.8 GB of working space.
- How fast is Spark-X2.6-4B on an RTX 4090?
- Fast: about 251 tokens per second (tok/s). Answers appear faster than you can read them. This is our estimate, not a measured test.
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate