- Size
- 4.1B parameterscounted from the safetensors header on the Hub
- Licence
- unknown, Apache License 2.0Our reading, check the licence: You can use, change and redistribute the model, including commercially. Keep the licence and any notices, and say which files you changed; you do not have to publish your changes. It includes a patent licence that ends for anyone who sues over patents in the work.
- On the Hub since
- 19 Oct 2026the date the repo was created
- Context length
- 1M tokensfrom the model's config
- Fine-tune
- of XHToken/Spark-X2.6-4B-BaseSpark2_5ForCausalLM
- On Hugging Face
- XHToken/Spark-X2.6-4B35k downloads in the last 30 days, 1.1k likes
Scores
No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.33 GB, worked out from the model's config (XHToken/Spark-X2.6-4B), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
XHToken/Spark-X2.6-4B-GGUF (the maker's own conversion), 882k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q4_K_M | 3.3 GBfile size | 4.1 GB3.3 + 0.33 + 0.50 | Commandsllama.cpp llama-server -hf XHToken/Spark-X2.6-4B-GGUF:Q4_K_MOllama ollama run hf.co/XHToken/Spark-X2.6-4B-GGUF:Q4_K_MDownload hf download XHToken/Spark-X2.6-4B-GGUF --include "Spark-X2.6-4B-Q4_K_M.gguf" --local-dir Spark-X2.6-4B-GGUF |
| Q8_0 | 4.1 GBfile size | 4.9 GB4.1 + 0.33 + 0.50 | Commandsllama.cpp llama-server -hf XHToken/Spark-X2.6-4B-GGUF:Q8_0Ollama ollama run hf.co/XHToken/Spark-X2.6-4B-GGUF:Q8_0Download hf download XHToken/Spark-X2.6-4B-GGUF --include "Spark-X2.6-4B-Q8_0.gguf" --local-dir Spark-X2.6-4B-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitabenzerps/Spark-X2.6-4B-MLX-4bit | 2.2 GBfile size | 3.0 GB2.2 + 0.33 + 0.50 | Download page |
| MLX 4bitmlx-community/Spark-X2.6-4B-OptiQ-4bit | 2.8 GBfile size | 3.7 GB2.8 + 0.33 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 7.7 GBfile size | 8.5 GB7.7 + 0.33 + 0.50 |
hf download XHToken/Spark-X2.6-4B --local-dir Spark-X2.6-4BOther conversions (9; sizes not read)
- XHToken/Spark-X2.6-4B-DSpark-GGUF GGUF, by the maker, 5.2k downloads
- XHToken/Spark-X2.6-4B-FP8 FP8, by the maker, 2.2k downloads
- XHToken/Spark-X2.6-4B-INT4 Other, int4, by the maker, 1.1k downloads
- XHToken/Spark-X2.6-4B-INT8 Other, int8, by the maker, 1.1k downloads
- infosave/Spark-X2.6-4B-cmf Other, 1.3k downloads
- mohdmahmodi/Spark-X2.6-4B-ONNX-WebGPU Other, 1.1k downloads
- cyankiwi/Spark-X2.6-4B-AWQ-INT4 AWQ, int4, 241 downloads
- UnstableLlama/Spark-X2.6-4B-exl3 EXL3, 58 downloads
- Xylolabs/Spark-X2.6-4B-Tenstorrent-Tensix-BFP4-GPTQ GPTQ, 42 downloads
The Hub tags 71 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Fine-tunes of this model
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- JuneoAI/Laplace-1-Vector4.1B21kUnreviewed
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.