Bielik 11B v3.0 (multilingual) — 显存、速度与本地部署
作者： Jakub Rusinowski · 最后更新：
The original Bielik 11B v3 with the multilingual tokenizer, trained across 32 European languages with Polish emphasis. For Polish-only work the PL build, with SpeakLeash's APT4 tokenizer, fits more Polish text into the same context. SpeakLeash publishes a DFlash speculative-decoding drafter for it. Gated repository; Apache-2.0.
Bielik 11B v3.0 (multilingual) 在 Q4_K_M 下约需 8 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)。包含 8K 上下文的 KV 缓存，因此数值高于上方的主数字。
| 量化 | 显存 | 显存 | 速度（估算） | 适配 |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 6.1 GB | ~122 tok/s | 可运行 | |
| Q3_K_M 3.41 bpw | 7.2 GB | ~104 tok/s | 可运行 | |
| Q4_K_M 4.83 bpw | 9.2 GB | ~81 tok/s | 可运行 | |
| Q5_K_M 5.67 bpw | 10.4 GB | ~72 tok/s | 可运行 | |
| Q6_K 6.56 bpw | 11.6 GB | ~65 tok/s | 可运行 | |
| Q8_0 8.50 bpw | 14.3 GB | ~52 tok/s | 可运行 | |
| F16 16.00 bpw | 24.8 GB | ~5 tok/s | 需卸载 |
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 11B v3.0 (multilingual) 显存计算器 →
运行 Bielik 11B v3.0 (multilingual)
目录中能运行 Bielik 11B v3.0 (multilingual) 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 11B v3.0 (multilingual)
安装 Ollama，然后运行：
ollama run bielik规格
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- 参数量
- 11 Billion
- 上下文窗口
- 32,768
- 架构
- Dense transformer (50 layers, GQA)
- 提供商
- SpeakLeash / ACK Cyfronet AGH
- 许可证
- Apache-2.0
- Availability
- Weights downloadable
- Access
- Gated: request access on Hugging Face and accept the licence first
- Practical deployment
- Laptop
- 规格量化
- Q4_K_M
- 系统内存
- 16 GB
- 记录更新于
- 2026-11-11
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 的其他尺寸
Bielik 11B v3.0 (multilingual) — 常见问题
How much VRAM does Bielik 11B v3.0 (multilingual) need?
About 8 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 11B v3.0 (multilingual) run on an RTX 4090 (24 GB)?
Yes. Bielik 11B v3.0 (multilingual) needs about 8 GB at Q4_K_M, inside a 24 GB card, at an estimated 81 tokens/sec.
How do I run Bielik 11B v3.0 (multilingual) 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.
What other sizes does Bielik come in?
Bielik PL 11B v3.0 Instruct (7 GB), Bielik 11B v3.1 Instruct (8 GB), Bielik 11B v3.0 (multilingual) (8 GB), Bielik Minitron 7B v3.0 Instruct (5 GB), Bielik PL Minitron 7B v3.0 Instruct (5 GB), Bielik 4.5B v3.0 Instruct (4 GB), Bielik 1.5B v3.0 Instruct (2 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.