Thinking Machines26.4B (3.4B active)NVFP4 + MXFP8 (mixed) 下约 21 GB 显存
许可证: Apache-2.0本地运行: 官方本地运行硬件: 消费级本地成熟度: 早期版本证据: 有限

证据: 基准测试结果由厂商自行报告

Inkling 2 Mini — 显存、速度与本地部署

作者: Jakub Rusinowski · 最后更新:

Thinking Machines' first looped model: 24 layers whose middle 12 run three times per token, so 26.4B parameters (3.4B active, about 5.4B effective with the loops) do the work of a deeper network. It takes text and images, has a 1M-token context, and ships as one ~20 GB checkpoint in mixed NVFP4/MXFP8 that runs on a DGX Spark or a Mac with 32 GB or more. Ollama carries it as inkling-2-mini:26b-a5b, and llama.cpp loads the ggml-org GGUF files.

Inkling 2 Mini 在 NVFP4 + MXFP8 (mixed) 下约需 21 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。

运行 Inkling 2 Mini

目录中能运行 Inkling 2 Mini 的最便宜 GPU 是 AMD Radeon RX 7900 XTX (24 GB).

购买此硬件 AMD Radeon RX 7900 XTX 24GB — 24 GB VRAM · 355 W board power立即云端部署 RunPod 上的 RTX 4090 — 低至 $0.34/小时 · 价格核实于 2026-07

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。

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买,LLM Configurator 可能会获得佣金,而你无需支付任何额外费用。作为亚马逊联盟成员(Amazon Associate),LLM Configurator 会从符合条件的购买中获得收益。
AMD Radeon RX 7900 XTX 24GB
24 GB VRAM · 355 W board power
2026年价格波动较大——请以当前商品页价格为准。

如何运行 Inkling 2 Mini

安装 Ollama,然后运行:

ollama run inkling-2-mini:26b-a5b
Hugging Face 上的权重: thinkingmachines/Inkling-2-Mini ↗

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
26.4 Billion (3.4B active, ~5.4B effective)
上下文窗口
1,048,576
架构
Looped Mixture-of-Experts (128 experts, 8 active): 24 layers, middle 12 run 3x per token; vision encoder
提供商
Thinking Machines
许可证
Apache-2.0
Availability
Weights downloadable
Practical deployment
Single consumer GPU
规格量化
NVFP4 + MXFP8 (mixed)
系统内存
32 GB
记录更新于
2026-11-21
许可证Apache-2.0允许商业使用

Commercial use permitted. No usage restrictions beyond attribution.

限制与注意事项

  • Looped layers run three times per token and each pass keeps its own cache, which this site's memory and speed model cannot yet express: memory shown is the published file size, with no speed estimate.
  • Thinking Machines warns it can get stuck in long reasoning loops, especially when debugging code; set limits on output tokens and agent turns.
  • Released 20 November 2026; benchmarks on the card are vendor-reported.

另请参阅 Inkling 2 Small

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。

最适合agentscodingvisionon device

我的 GPU 能运行 Inkling 2 Mini 吗?

Inkling 的其他尺寸

Inkling 2 Mini — 常见问题

How much VRAM does Inkling 2 Mini need?

About 21 GB at NVFP4 + MXFP8 (mixed) — quantized weights plus framework overhead, before any KV cache. We publish no context-length figure or speed for it: its middle 12 layers run three times per token and each pass keeps its own cache, so the bytes read per token are not the weights once, which our memory and speed model cannot yet express. Apple Silicon counts unified memory toward the same figure.

Does Inkling 2 Mini run on an RTX 4090 (24 GB)?

Its weights and overhead come to about 21 GB at NVFP4 + MXFP8 (mixed), but we do not publish a fit verdict or a speed for it: its middle 12 layers run three times per token and each pass keeps its own cache, so the bytes read per token are not the weights once, which our memory and speed model cannot yet express.

How do I run Inkling 2 Mini locally?

Install Ollama and run `ollama run inkling-2-mini:26b-a5b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does Inkling come in?

Inkling (NVFP4) (589 GB), Inkling (BF16) (589 GB), Inkling Small (161 GB), Inkling 2 Small (394 GB), Inkling 2 Mini (21 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.