1-bit Bonsai 27B — 显存、速度与本地部署
作者: Jakub Rusinowski · 最后更新:
The phone build. Binary {−1, +1} weights at ~1.125 bits/weight bring a full 27B multimodal model down to 3.9 GB — small enough to run on an iPhone 17 Pro at ~11 tok/s. PrismML reports it keeps more than 90% of the FP16 baseline (MATH 91.66, coding 81.88); tool-calling is the weak spot, dropping from ~80 to ~66. Ships as GGUF (llama.cpp / LM Studio) and MLX (Apple). Specs from launch coverage — verify on the Hugging Face model card.
1-bit Bonsai 27B 在 1-bit (binary, ~1.125 bpw) 下约需 5 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 |
|---|---|---|---|---|
| 1-bit (binary, ~1.125 bpw) 1.13 bpw | 4.6 GB | ~119 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. 1-bit Bonsai 27B 显存计算器 →
运行 1-bit Bonsai 27B
目录中能运行 1-bit Bonsai 27B 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 1-bit Bonsai 27B
安装 Ollama,然后运行:
ollama run bonsai-27b规格
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
- 参数量
- 27 Billion
- 上下文窗口
- 262,144
- 架构
- Qwen3.6-27B (multimodal), 1-bit binary weights
- 提供商
- PrismML
- 许可证
- Apache 2.0
- Practical deployment
- Edge device (phone, SBC)
- 规格量化
- 1-bit (binary, ~1.125 bpw)
- 系统内存
- 8 GB
- 记录更新于
- 2026-07-15
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。
| 基准 | 分数 | 来源 |
|---|---|---|
| MATH | 91.66 % | 厂商声称 · PrismML (launch) |
| Coding (HumanEval+ class) | 81.88 % | 厂商声称 · PrismML (launch) |
| Tool-calling (BFCL class) | 66 % | 厂商声称 · PrismML (launch) |
我的 GPU 能运行 1-bit Bonsai 27B 吗?
- 1-bit Bonsai 27B 在 AMD Radeon RX 9060 XT 8GB 上
- 1-bit Bonsai 27B 在 Intel Arc B570 上
- 1-bit Bonsai 27B 在 Intel Arc B580 上
- 1-bit Bonsai 27B 在 NVIDIA GeForce RTX 3060 (12GB) 上
- 1-bit Bonsai 27B 在 NVIDIA GeForce RTX 3070 上
- 1-bit Bonsai 27B 在 NVIDIA GeForce RTX 3070 Ti 上
- 1-bit Bonsai 27B 在 NVIDIA GeForce RTX 3080 (10GB) 上
- 1-bit Bonsai 27B 在 NVIDIA GeForce RTX 4060 上
- 1-bit Bonsai 27B 在 NVIDIA GeForce RTX 4070 上
- 1-bit Bonsai 27B 在 NVIDIA GeForce RTX 4070 Super 上
- 1-bit Bonsai 27B 在 NVIDIA GeForce RTX 4070 Ti 上
- 1-bit Bonsai 27B 在 NVIDIA GeForce RTX 5060 上
- 1-bit Bonsai 27B 在 NVIDIA GeForce RTX 5060 Ti 8GB 上
- 1-bit Bonsai 27B 在 NVIDIA GeForce RTX 5070 上
Bonsai 27B 的其他尺寸
1-bit Bonsai 27B — 常见问题
How much VRAM does 1-bit Bonsai 27B need?
About 5 GB at 1-bit (binary, ~1.125 bpw) — 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 1-bit Bonsai 27B run on an RTX 4090 (24 GB)?
Yes. 1-bit Bonsai 27B needs about 5 GB at 1-bit (binary, ~1.125 bpw), inside a 24 GB card, at an estimated 119 tokens/sec.
How do I run 1-bit Bonsai 27B locally?
Install Ollama and run `ollama run bonsai-27b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Bonsai 27B come in?
1-bit Bonsai 27B (5 GB), Ternary Bonsai 27B (7 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.