qwen3 4b pokerbench grpo needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.5 GB (Q4_K_M) to 8.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Qwen3-4B PokerBench GRPO – poker decision‑making model
Qwen3-4B PokerBench GRPO is a 4B‑parameter model fine‑tuned for poker decision making. It uses SFT on high‑quality reasoning traces followed by GRPO reinforcement learning with an LLM‑as‑judge reward. The model outputs structured reasoning and a poker action.
Good at
- Poker strategy reasoning
- Structured action output
- LLM‑as‑judge reinforcement
Limits
- No vision support
- Requires 8k context for estimates
- Apache‑2.0 license
Best for
- Poker training simulations
- AI poker bots
- Decision‑making research
Who it’s for. Developers building poker AI or researchers studying reinforcement learning in card games. The model is suitable for applications that need structured reasoning and action generation in poker contexts.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q8_0 | 4.3 GB | 6.0 GB | Fits | Get file → | |
| F16 | 8.1 GB | 9.8 GB | Too big | Get file → |
For 8 GB VRAM use the Q4_K_M quant (file size 2.5 GB, estimated memory 4.2 GB). If 12 GB VRAM is available, Q8_0 (4.28 GB, 6 GB memory) offers higher precision. The F16 quant (8.05 GB, 9.8 GB memory) requires more memory and is best for high‑end setups.
What GPU do you need for qwen3 4b pokerbench grpo?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (8.1 GB file, about 9.8 GB in use).
Which qwen3 4b pokerbench grpo quant should you choose?
Q4_K_M is the usual starting point for qwen3 4b pokerbench grpo: it balances file size and quality well. Here it is a 2.5 GB file.
The Q8_0 file is 4.3 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about qwen3 4b pokerbench grpo
How much VRAM does qwen3 4b pokerbench grpo need?
About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run qwen3 4b pokerbench grpo on an 8 GB GPU?
Yes, with Q8_0: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of qwen3 4b pokerbench grpo GGUF?
It depends on the quant: Q4_K_M is 2.5 GB, Q8_0 is 4.3 GB, F16 is 8.1 GB.
What context length does qwen3 4b pokerbench grpo support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download qwen3 4b pokerbench grpo GGUF?
The files are on Hugging Face in the YiPz/qwen3-4b-pokerbench-grpo-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does qwen3 4b pokerbench grpo use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Qwen3-4B PokerBench GRPO on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 4.2 GB memory at 8k context, fitting within 8 GB VRAM.
Does the model support vision inputs?
No, the model has no vision capability.
What license applies to this model?
The model is released under the Apache‑2.0 license.