- Size
- 31.2B parameters, 4.0B active (from the repo name)counted 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
- 16 Sep 2026the date the repo was created
- Context length
- 256k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)Xing4_0ForCausalLM
- On Hugging Face
- XingChen-AGI/Xing4.0-29B-A4B5.8k downloads in the last 30 days, 1.9k 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: 0.35 GB, worked out from the model's config (XingChen-AGI/Xing4.0-29B-A4B), 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
Venastine-Research/Xing4.0-29B-A4B-GGUF (converted by Venastine-Research), 24k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ2_M | 9.2 GBfile size | 10.1 GB9.2 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf Venastine-Research/Xing4.0-29B-A4B-GGUF:IQ2_MOllama ollama run hf.co/Venastine-Research/Xing4.0-29B-A4B-GGUF:IQ2_MDownload hf download Venastine-Research/Xing4.0-29B-A4B-GGUF --include "Xing4.0-29B-A4B-IQ2_M.gguf" --local-dir Xing4.0-29B-A4B-GGUF |
| IQ3_XXS | 10.8 GBfile size | 11.6 GB10.8 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf Venastine-Research/Xing4.0-29B-A4B-GGUF:IQ3_XXSOllama ollama run hf.co/Venastine-Research/Xing4.0-29B-A4B-GGUF:IQ3_XXSDownload hf download Venastine-Research/Xing4.0-29B-A4B-GGUF --include "Xing4.0-29B-A4B-IQ3_XXS.gguf" --local-dir Xing4.0-29B-A4B-GGUF |
| IQ3_M | 12.2 GBfile size | 13.1 GB12.2 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf Venastine-Research/Xing4.0-29B-A4B-GGUF:IQ3_MOllama ollama run hf.co/Venastine-Research/Xing4.0-29B-A4B-GGUF:IQ3_MDownload hf download Venastine-Research/Xing4.0-29B-A4B-GGUF --include "Xing4.0-29B-A4B-IQ3_M.gguf" --local-dir Xing4.0-29B-A4B-GGUF |
| Q4_K_M | 17.6 GBfile size | 18.5 GB17.6 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf Venastine-Research/Xing4.0-29B-A4B-GGUF:Q4_K_MOllama ollama run hf.co/Venastine-Research/Xing4.0-29B-A4B-GGUF:Q4_K_MDownload hf download Venastine-Research/Xing4.0-29B-A4B-GGUF --include "Xing4.0-29B-A4B-Q4_K_M.gguf" --local-dir Xing4.0-29B-A4B-GGUF |
| Q5_K_M | 20.7 GBfile size | 21.5 GB20.7 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf Venastine-Research/Xing4.0-29B-A4B-GGUF:Q5_K_MOllama ollama run hf.co/Venastine-Research/Xing4.0-29B-A4B-GGUF:Q5_K_MDownload hf download Venastine-Research/Xing4.0-29B-A4B-GGUF --include "Xing4.0-29B-A4B-Q5_K_M.gguf" --local-dir Xing4.0-29B-A4B-GGUF |
| Q6_K | 23.9 GBfile size | 24.8 GB23.9 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf Venastine-Research/Xing4.0-29B-A4B-GGUF:Q6_KOllama ollama run hf.co/Venastine-Research/Xing4.0-29B-A4B-GGUF:Q6_KDownload hf download Venastine-Research/Xing4.0-29B-A4B-GGUF --include "Xing4.0-29B-A4B-Q6_K.gguf" --local-dir Xing4.0-29B-A4B-GGUF |
| Q8_0 | 30.9 GBfile size | 31.8 GB30.9 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf Venastine-Research/Xing4.0-29B-A4B-GGUF:Q8_0Ollama ollama run hf.co/Venastine-Research/Xing4.0-29B-A4B-GGUF:Q8_0Download hf download Venastine-Research/Xing4.0-29B-A4B-GGUF --include "Xing4.0-29B-A4B-Q8_0.gguf" --local-dir Xing4.0-29B-A4B-GGUF |
| F16 | 58.2 GBfile size | 59.0 GB58.2 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf Venastine-Research/Xing4.0-29B-A4B-GGUF:F16Ollama ollama run hf.co/Venastine-Research/Xing4.0-29B-A4B-GGUF:F16Download hf download Venastine-Research/Xing4.0-29B-A4B-GGUF --include "Xing4.0-29B-A4B-f16.gguf" --local-dir Xing4.0-29B-A4B-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitTokenAI-zer/Xing4.0-29B-A4B-4bit-MLX | 15.5 GBfile size | 16.4 GB15.5 + 0.35 + 0.50 | Download page |
| MLX 4bitmlx-community/Xing4.0-29B-A4B-OptiQ-4bit | 19.2 GBfile size | 20.0 GB19.2 + 0.35 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 58.1 GBfile size | 59.0 GB58.1 + 0.35 + 0.50 |
hf download XingChen-AGI/Xing4.0-29B-A4B --local-dir Xing4.0-29B-A4BOther conversions (2; sizes not read)
- XingChen-AGI/Xing4.0-29B-A4B-w8a8 Other, w8a8, by the maker, 952 downloads
- XingChen-AGI/Xing4.0-29B-A4B-FP8 FP8, by the maker, 359 downloads
The Hub tags 19 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.
- XingChen-AGI/Xing4.0-29B-Intent31.2B6.1kUnreviewed
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.