deploy-kimi-k26-on-rtx-pro-6000 SKILL.md skillA
deploy-kimi-k26-on-rtx-pro-6000 from soulmachine/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add soulmachine/skills/deploy-kimi-k26-on-rtx-pro-6000@git:20260615.d2529b6Pins git:20260615.d2529b6 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- soulmachine/skills
- Path
deploy-kimi-k26-on-rtx-pro-6000/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260615.d2529b6, committed Jun 15, 2026
- First version recorded
- Jun 12, 2026
- Size
- 19,192 bytes
- Repository stars
- 3
- License
- MIT
Deploy and serve Moonshot Kimi-K2.6 (1T MoE, MLA, 256K context, vision) in a user-chosen quantization — official INT4 QAT (moonshotai/Kimi-K2.6, compressed-tensors→Marlin; vLLM or SGLang) or NVFP4 (nvidia/Kimi-K2.6-NVFP4, ModelOpt FP4; vLLM only — SGLang NVFP4 is NaN-broken on sm_120) — on a Linux server (verified Ubuntu 26.04) with 8× NVIDIA RTX PRO 6000 Blackwell Server Edition (96 GB, sm_120) GPUs. The quantization and the engine are both chosen at deploy time with a hardware-based…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Deploy Kimi-K2.6 (INT4 QAT or NVFP4) on 8× RTX PRO 6000 Blackwell Server Edition (sm_120) Serve **Kimi-K2.6** (1T MoE; MLA; 256K; MoonViT vision) in a **user-chosen quantization**, with an **official-image Docker** container — OpenAI-compatible API on `:30000`, **TP=8**, weights bind-mounted read-only from local NVMe, all in VRAM. Both the **quantization** and the **engine** are chosen at deploy time (steps 2–3) with a hardware-based recommendation: - **INT4 QAT** — [moonshotai/Kimi-K2.6](https://huggingface.co/moonshotai/Kimi-K2.6); compressed-tensors → **Marlin** (auto); **vLLM or SGLang**; stock images, no patch. **Recommended on sm_120** (official, simplest, both engines verified). - **NVFP4** — [nvidia/Kimi-K2.6-NVFP4](https://huggingface.co/nvidia/Kimi-K2.6-NVFP4); ModelOpt FP4 (`--quantization modelopt_fp4`); **vLLM only** (SGLang NVFP4 = NaN on sm_120). Needs a **patched CUDA-13 image** (`build_nvfp4_image.sh`) + **offline remote-code prep** (`prep_remote_code.sh`). On sm_120 it gives **no throughput win** (PCIe-comm-bound: Marlin ≈ native b12x, native is actually ~12% slower) — prefer it on **datacenter Blackwell (sm_100/B200)** where native FP4 (cutedsl) is tuned, or… …
Read the whole file at its exact version.
How to install
mdr add soulmachine/skills/deploy-kimi-k26-on-rtx-pro-6000@sha256:d1899346496901c0The line at the top of this page pins the label git:20260615.d2529b6, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ivobq5rg3exslx6j)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jun 12, 2026 and Jun 15, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260615.d2529b6 latest | 2026-06-15 | d2529b6 | 19,192 B | A | view · diff |
| git:20260613.d71ed01 | 2026-06-13 | d71ed01 | 18,295 B | A | view · diff |
| git:20260612.204f18b | 2026-06-12 | 204f18b | 15,591 B | A | view · diff |
| git:20260612.8f2cc39 | 2026-06-12 | 8f2cc39 | 14,116 B | A | view · diff |
| git:20260612.e2f01f6 | 2026-06-12 | e2f01f6 | 13,480 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (19192 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
soulmachine/skills · 3 stars · license MIT · pushed 2026-10-31 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ivobq5rg3exslx6j GET https://markdownregistry.com/api/v1/resolve?ref=soulmachine/skills/deploy-kimi-k26-on-rtx-pro-6000 GET https://markdownregistry.com/api/v1/blob/d1899346496901c0b40f36baf1006535a11686e2f027303f4ca3d1f529bbdac9
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.