Bielik PL 11B v3.0 Instruct — 显存、速度与本地部署
作者： Jakub Rusinowski · 最后更新：
11B instruct model trained across 32 European languages with Polish cherry-picked and processed by hand. The APT4 tokenizer encodes Polish in fewer tokens than a general vocabulary, so a given context window holds more Polish text. Fits a 12 GB card at Q4.
Bielik PL 11B v3.0 Instruct 在 Q4_K_M 下约需 7 GB 显存——量化权重加框架开销，不含 KV 缓存。在 Apple Silicon 上，这部分来自统一内存。
按量化级别的显存与速度
计算基准：NVIDIA RTX 4090 (24 GB)。仅含权重与开销：该模型架构未公开，因此未计入 KV 缓存。
| 量化 | 显存 | 显存 | 速度（估算） | 适配 |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 4.4 GB | ~127 tok/s | 可运行 | |
| Q3_K_M 3.41 bpw | 5.5 GB | ~108 tok/s | 可运行 | |
| Q4_K_M 4.83 bpw | 7.4 GB | ~84 tok/s | 可运行 | |
| Q5_K_M 5.67 bpw | 8.6 GB | ~75 tok/s | 可运行 | |
| Q6_K 6.56 bpw | 9.8 GB | ~67 tok/s | 可运行 | |
| Q8_0 8.50 bpw | 12.5 GB | ~54 tok/s | 可运行 | |
| F16 16.00 bpw | 22.8 GB | ~31 tok/s | 勉强 |
黑色标记 = NVIDIA RTX 4090 (24 GB) 上的可用显存。 估算来自内存带宽屋顶线模型，详见 方法说明页. Bielik PL 11B v3.0 Instruct 显存计算器 →
运行 Bielik PL 11B v3.0 Instruct
目录中能运行 Bielik PL 11B v3.0 Instruct 的最便宜 GPU 是 Intel Arc B570 (10 GB).
或在 Vast.ai 比较，低至 $0.35/小时 (typical low · varies)
作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。
如何运行 Bielik PL 11B v3.0 Instruct
安装 Ollama，然后运行：
ollama run bielik规格
Corroborated — Two or more independent sources agree on these figures, but the model card itself was not retrieved. Treat the numbers as good rather than confirmed. 尚未确认： license, context, releaseDate.
- 参数量
- 11 Billion
- 上下文窗口
- 32,768
- 架构
- Dense
- 提供商
- SpeakLeash / ACK Cyfronet AGH
- 许可证
- Apache 2.0
- 规格量化
- Q4_K_M
- 系统内存
- 16 GB
- 记录更新于
- 2026-09-19
Commercial use permitted. No usage restrictions beyond attribution.
质量与使用场景
评分由模型作者或独立评测方发布——衡量质量而非吞吐量，并非我们实测。
Bielik PL 11B v3.0 Instruct — 常见问题
How much VRAM does Bielik PL 11B v3.0 Instruct need?
About 7 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Bielik PL 11B v3.0 Instruct run on an RTX 4090 (24 GB)?
Yes. Bielik PL 11B v3.0 Instruct needs about 7 GB at Q4_K_M, inside a 24 GB card, at an estimated 84 tokens/sec.
How do I run Bielik PL 11B v3.0 Instruct locally?
Install Ollama and run `ollama run bielik`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.