Spark-X2.6-4B-FP8 is an open-weight model for text generation from SparkLLM, released under Apache License 2.0. It has 4.1B parameters. At 16-bit it needs about 9.9 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Parameters4.1B
Context—
Weights—
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve Spark-X2.6-4B-FP8 (4.1B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 8.2 GB | 9.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 4.1 GB | 4.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 2.1 GB | 2.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 22, 2026.
Spark-X2.6-4B-FP8 on every accelerator the SAVRN Index prices, at every precision
Model Card
Identity and Version
- Repository
- XHToken/Spark-X2.6-4B-FP8
- Publisher
- SparkLLM
- Task
- Text generation
- Modality
- Text
- Library
- transformers
- Parameters
- 4.1B parameters
- Languages
- en, zh
- Revision
- 49889320dc2d74a1623a72a56a7d987385fc91d6
- First published
- 2026-10-20
- Last updated
- 2026-10-21
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
Download from SparkLLM
Released by SparkLLM through its official repository on Hugging Face. Read the license.
Built From
- Derived from XHToken/Spark-X2.6-4B
- Quantized from XHToken/Spark-X2.6-4B
Memory Requirements
| Precision | Weights in memory |
|---|---|
| 16-bit | 8.2 GB |
| 8-bit | 4.1 GB |
| 4-bit | 2.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Spark-X2.6-4B-FP8
How much GPU memory does Spark-X2.6-4B-FP8 need?
About 9.9 GB at 16-bit and 2.5 GB at 4-bit: the weights (4.1B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Spark-X2.6-4B-FP8 on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use Spark-X2.6-4B-FP8 commercially?
Yes. Spark-X2.6-4B-FP8 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
Qwen3-8B after full-parameter supervised fine-tuning for mathematical keyword and meaning generation. This is the exact saved epoch 4 checkpoint at optimizer step 2976. The repository contains the model weights, configuration, and tokenizer files for inference. Training dataset: devpotatopotato/math-keyword-training, keyword-261001-bigmath-gpt-6-sol.jsonl. Use the tokenizer chat template with enablethinking=False. Pass the following template as a user message and replace {problem} with the problem text
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and…
We introduce the updated version of the Qwen3-4B non-thinking mode, named Qwen3-4B-Instruct-2507, featuring the following key enhancements: - Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage. - Substantial gains in long-tail knowledge coverage across multiple languages. - Markedly better alignment with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text generation. - Enhanced capabilities in 256K long-context understanding. Qwen3-4B-Instruct-2507 has the following features: NOTE: This model supports only non-thinking…
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Building upon extensive advancements in training data, model architecture, and optimization techniques, Qwen3 delivers the following key improvements over the previously released Qwen2.5: Qwen3-4B-Base has the following features: For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation. The code of Qwen3 has been in the latest Hugging Face transformers and we advise you to use the latest version of transformers. With transformers<4.51.0, you will…
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Building upon extensive advancements in training data, model architecture, and optimization techniques, Qwen3 delivers the following key improvements over the previously released Qwen2.5: Qwen3-4B-Base has the following features: For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation. The code of Qwen3 has been in the latest Hugging Face transformers and we advise you to use the latest version of transformers. With transformers<4.51.0, you will…