Bielik 4.5B v3.0 Instruct — 显存、速度与本地部署
作者： Jakub Rusinowski · 最后更新：
A 4.6B Bielik v3 for laptops and integrated graphics, Polish-first with European languages, ChatML prompt format and an 8,192-token context. SpeakLeash publishes official GGUF, FP8 and MLX builds. Gated repository; Apache-2.0.
Bielik 4.5B v3.0 Instruct 在 Q4_K_M 下约需 4 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 | 2.9 GB | ~215 tok/s | 可运行 | |
| Q3_K_M 3.41 bpw | 3.3 GB | ~190 tok/s | 可运行 | |
| Q4_K_M 4.83 bpw | 4.2 GB | ~157 tok/s | 可运行 | |
| Q5_K_M 5.67 bpw | 4.7 GB | ~142 tok/s | 可运行 | |
| Q6_K 6.56 bpw | 5.2 GB | ~129 tok/s | 可运行 | |
| Q8_0 8.50 bpw | 6.4 GB | ~108 tok/s | 可运行 | |
| F16 16.00 bpw | 10.8 GB | ~66 tok/s | 可运行 |
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 4.5B v3.0 Instruct 显存计算器 →
运行 Bielik 4.5B v3.0 Instruct
目录中能运行 Bielik 4.5B 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 4.5B v3.0 Instruct
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. 尚未确认： context.
- 参数量
- 4.6 Billion
- 上下文窗口
- 8,192
- 架构
- Dense transformer (60 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
- Edge device (phone, SBC)
- 规格量化
- Q4_K_M
- 系统内存
- 8 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 4.5B v3.0 Instruct — 常见问题
How much VRAM does Bielik 4.5B v3.0 Instruct need?
About 4 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 4.5B v3.0 Instruct run on an RTX 4090 (24 GB)?
Yes. Bielik 4.5B v3.0 Instruct needs about 4 GB at Q4_K_M, inside a 24 GB card, at an estimated 157 tokens/sec.
How do I run Bielik 4.5B 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.
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.