Nemotron 3.5 Bolt 74B — 显存、速度与本地部署
作者： Jakub Rusinowski · 最后更新：
NVIDIA's local-agent model for RTX Spark laptops, compressed from Nemotron 3.5 Super VL (120B-A12B): 74B parameters, 9B active (top-9 experts), in a hybrid stack of 40 Mamba-2, 40 latent-MoE and only 8 attention blocks, so its KV cache is about a tenth of a same-depth transformer's. Takes text, images and video; 262,144-token context. The official local build is a 2-bit GGUF (experts at IQ2_XXS, recovered with quantisation-aware distillation): 22.0 GB, plus a 1.7 GB vision projector. NVIDIA calls it the "24GB" version, but its own card lists RTX GPUs with 32 GB or more, with 28 GB and 32 GB recipes; on a 24 GB card it is tight. Ships with a LiLiCorr speculative-decoding drafter.
Nemotron 3.5 Bolt 74B 在 IQ2_XXS QAD 下约需 23 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 |
|---|---|---|---|---|
| IQ2_XXS QAD 2.38 bpw | 22.9 GB | ~171 tok/s | 勉强 | |
| BF16 16.00 bpw | 150.6 GB | — | 放不下 |
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. Nemotron 3.5 Bolt 74B 显存计算器 →
运行 Nemotron 3.5 Bolt 74B
目录中能运行 Nemotron 3.5 Bolt 74B 的最便宜 GPU 是 NVIDIA GeForce RTX 5090 (32 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 Nemotron 3.5 Bolt 74B
安装 Ollama，然后运行：
ollama run nemotron-3.5-bolt:74b-a9b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： arch.kv_layers.
- 参数量
- 74 Billion (9B active)
- 上下文窗口
- 262,144
- 架构
- Hybrid Mamba-2 + latent MoE + attention (8 of 88 blocks attend), vision encoder
- 提供商
- NVIDIA
- 许可证
- OpenMDW-1.1
- Availability
- Weights downloadable
- Practical deployment
- Single consumer GPU
- 规格量化
- IQ2_XXS QAD
- Vision projector
- +1.7 GB when you send images (not included above)
- 系统内存
- 32 GB
- 记录更新于
- 2026-10-15
Commercial use permitted. No usage restrictions beyond attribution.
限制与注意事项
- The "24GB" name is the file footprint (22.0 GB weights + 1.7 GB vision projector). NVIDIA's own deployment table starts at 32 GB GPUs.
- Only one local quantisation is published (NVIDIA's 2-bit QAD build); the BF16 checkpoint is meant for fine-tuning, not local inference.
- LM Studio support is reported in launch coverage but not on the model card.
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。
我的 GPU 能运行 Nemotron 3.5 Bolt 74B 吗？
Nemotron 3.5 的其他尺寸
Nemotron 3.5 Bolt 74B — 常见问题
How much VRAM does Nemotron 3.5 Bolt 74B need?
About 23 GB at IQ2_XXS QAD — 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 Nemotron 3.5 Bolt 74B run on an RTX 4090 (24 GB)?
Yes. Nemotron 3.5 Bolt 74B needs about 23 GB at IQ2_XXS QAD, inside a 24 GB card, at an estimated 171 tokens/sec.
How do I run Nemotron 3.5 Bolt 74B locally?
Install Ollama and run `ollama run nemotron-3.5-bolt:74b-a9b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Nemotron 3.5 come in?
Nemotron 3.5 Lightning 30B-A3B (19 GB), Nemotron 3.5 Bolt 74B (23 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.