Qwen · fine-tune of Qwen/Qwen3.5-35B-A3B-Base
Qwen-AgentWorld-35B-A3B
Runs on your machine
Choose a machine
We then show the largest format that fits, from real file sizes where we have them.
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: 0.16 GB, worked out from the model's config (Qwen/Qwen-AgentWorld-35B-A3B), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
weights context cache runtime
GGUF for llama.cpp, Ollama, LM Studio and others
unsloth/Qwen-AgentWorld-35B-A3B-GGUF (converted by unsloth), 88k downloads. Sizes are the real files on the Hub, all parts added up. Showing the common levels.
| Format | Size | Memory needed | Memory | Get it |
|---|---|---|---|---|
| UD-Q4_K_M | 20.6 GBfile size | 21.3 GB20.6 + 0.16 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen-AgentWorld-35B-A3B-GGUF:UD-Q4_K_MOllama ollama run hf.co/unsloth/Qwen-AgentWorld-35B-A3B-GGUF:UD-Q4_K_MDownload hf download unsloth/Qwen-AgentWorld-35B-A3B-GGUF --include "Qwen-AgentWorld-35B-A3B-UD-Q4_K_M.gguf" --local-dir Qwen-AgentWorld-35B-A3B-GGUF | |
| UD-Q5_K_M | 24.6 GBfile size | 25.3 GB24.6 + 0.16 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen-AgentWorld-35B-A3B-GGUF:UD-Q5_K_MOllama ollama run hf.co/unsloth/Qwen-AgentWorld-35B-A3B-GGUF:UD-Q5_K_MDownload hf download unsloth/Qwen-AgentWorld-35B-A3B-GGUF --include "Qwen-AgentWorld-35B-A3B-UD-Q5_K_M.gguf" --local-dir Qwen-AgentWorld-35B-A3B-GGUF | |
| UD-Q6_K | 27.3 GBfile size | 28.0 GB27.3 + 0.16 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen-AgentWorld-35B-A3B-GGUF:UD-Q6_KOllama ollama run hf.co/unsloth/Qwen-AgentWorld-35B-A3B-GGUF:UD-Q6_KDownload hf download unsloth/Qwen-AgentWorld-35B-A3B-GGUF --include "Qwen-AgentWorld-35B-A3B-UD-Q6_K.gguf" --local-dir Qwen-AgentWorld-35B-A3B-GGUF | |
| Q8_0 | 34.4 GBfile size | 35.0 GB34.4 + 0.16 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen-AgentWorld-35B-A3B-GGUF:Q8_0Ollama ollama run hf.co/unsloth/Qwen-AgentWorld-35B-A3B-GGUF:Q8_0Download hf download unsloth/Qwen-AgentWorld-35B-A3B-GGUF --include "Qwen-AgentWorld-35B-A3B-Q8_0.gguf" --local-dir Qwen-AgentWorld-35B-A3B-GGUF | |
| BF16 | 64.6 GBfile size, 2 parts | 65.3 GB64.6 + 0.16 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen-AgentWorld-35B-A3B-GGUF:BF16Download hf download unsloth/Qwen-AgentWorld-35B-A3B-GGUF --include "BF16/Qwen-AgentWorld-35B-A3B-BF16-*-of-00002.gguf" --local-dir Qwen-AgentWorld-35B-A3B-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| MLX mxfp4Brooooooklyn/Qwen-AgentWorld-35B-A3B-mxfp4-mlx | 21.7 GBfile size | 22.4 GB21.7 + 0.16 + 0.50 | Download page | |
| MLXBrooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q8_K_XL-mlx | 34.3 GBfile size | 35.0 GB34.3 + 0.16 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| BF16original weights | 64.6 GBfile size | 65.2 GB64.6 + 0.16 + 0.50 |
hf download Qwen/Qwen-AgentWorld-35B-A3B --local-dir Qwen-AgentWorld-35B-A3BOther conversions (9; sizes not read)
- cyankiwi/Qwen-AgentWorld-35B-A3B-AWQ-INT4 AWQ, int4, 141 downloads
- cyankiwi/Qwen-AgentWorld-35B-A3B-AWQ-FP8 AWQ, fp8, 135 downloads
- lovedheart/Qwen-AgentWorld-35B-A3B-NVFP4 NVFP4, 130 downloads
- lovedheart/Qwen-AgentWorld-35B-A3B-FP8 FP8, 95 downloads
- sakamakismile/Qwen-AgentWorld-35B-A3B-NVFP4 NVFP4, 56 downloads
- cyankiwi/Qwen-AgentWorld-35B-A3B-AWQ-NVFP4 AWQ, nvfp4, 35 downloads
- LeaderboardModel1/Qwen-AgentWorld-35B-A3B-AutoRound-W4A16-RTN Other, w4a16, 29 downloads
- Frosty40/Qwen-AgentWorld-35B-A3B-NVFP4 NVFP4, 21 downloads
- palmfuture/Qwen-AgentWorld-35B-A3B-NVFP4A16 NVFP4, 18 downloads
The Hub tags 75 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.
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, 15:15 UTC. The repo. Found a mistake on this page? Tell us.