cd /news/large-language-models/sampling-inkling-and-the-alias-patte… · home topics large-language-models article
[ARTICLE · art-83897] src=zackproser.com ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Sampling Inkling and the Alias Pattern

Thinking Machines' Inkling, a 975B total / 41B active MoE model with Apache 2.0 license and 1M context, is being trialed via a bash wrapper alias 'claude-inkling' that bridges Anthropic's CLI to the OpenAI messages format. The wrapper supports both Baseten direct endpoint and Vercel AI Gateway, with the direct route initially hitting rate limits (100k tokens/min) that interrupted work. The trial uses pass/fail sampling on real tasks, and Inkling's behavior matches its MoE spec: fast prefill, slower decode, and requiring a large output budget for reasoning.

read3 min views2 publishedAug 2, 2026
Sampling Inkling and the Alias Pattern
Image: Zackproser (auto-discovered)

In July I wrote The Model Sheet — how a filename like Qwen2.5-Coder-32B-Instruct-Q5_K_M.gguf breaks into family, domain, params, training stage, quantization, and format. Those fields predict behavior before you download. What comes after the spec sheet is the trial: load the weights, run a real prompt, see if the model behaves as advertised.

Lately that trial has been Thinking Machines' Inkling: 975B total / 41B active MoE, Apache 2.0, 1M context. Most modern open-weight releases now ship with the OpenAI messages format (system

/ user

/ assistant

roles with content

arrays). That is the only reason the claude-inkling

wrapper works. No translation layer needed — just point ANTHROPIC_BASE_URL

at the endpoint.

The Baseten route (and the rate limit that killed it)

Baseten's direct endpoint (https://inference.baseten.co

) has a native /v1/messages

route. For a verified workspace, it skips the Basic-tier rate cap (100k tokens/min) — a single Claude Code turn exhausts that instantly. The key lives at ~/.config/baseten/key

. The wrapper (~/.local/bin/claude-inkling

) reads it, exports the endpoint and model identifier (thinkingmachines/inkling

or inkling-small

), then executes claude

.

In early trials we hit the cap immediately. Reading files with Inkling Large consumed tokens fast enough that the rate limit interrupted work before anything finished. The fix was temporary: switch back to the Vercel AI Gateway (claude-gateway

) to complete the task. The Gateway pools through a single bill with provider failover, so the interruption was minimal. Once the workspace is verified or a dedicated deployment is provisioned, Baseten direct is the stable path. For now the wrapper supports both: INKLING_VIA=baseten

for direct, default for Gateway.

The alias: `claude-inkling`

The wrapper is a thin bash script. It exports Anthropic endpoint variables, disables telemetry and non-essential model calls (so local decode isn't wasted on background tasks), sets a generous output budget (32k by default), and executes claude

. Same pattern as claude-laguna

(local `llama-server`

) and `claude-deepseek`

(local DeepSeek V4-Flash via `ds4`

). One alias per model, one endpoint per alias, zero proxy overhead.

Because Inkling — like most new releases — speaks the OpenAI messages format, the client sends {"model":"thinkingmachines/inkling","messages":[...]}

and gets back {"type":"message","content":"..."} . The alias just bridges Anthropic's CLI naming convention and the provider's model registry.

What the trial looks like

Sampling is not a benchmark run. It is a short, representative task from real work — a coding snippet, a reasoning chain, a format conversion — scored pass or fail against a known answer. The model either produces working output or it doesn't. Binary. I keep the prompt set in a plain file under version control. The next release has to earn the swap.

Inkling's behavior so far aligns with its MoE spec: 41B active out of 975B total. Fast prefill, slower decode (bandwidth-bound, like any large model), and a generous output budget needed for reasoning spans before visible answers appear. That matches other reasoning-model releases — if max_tokens

is too small, the budget goes to hidden thinking and the content field returns empty. Fix: large token budget, or a non-reasoning variant for short replies.

This connects back to The Benchmark: a leaderboard rank collapses too many dimensions into one number. The fields from The Model Sheet — dense vs MoE, active params, quantization level, training stage — are the actual variables. The alias wrapper just makes them accessible to the CLI I already use.

Where this fits: the local lab keeps Llama-3.3-70B (storyteller) and Qwen2.5-Coder-32B (architect) hot on Metal via llama-server (llama70

:8080, coder32

:8081). The claude-inkling alias is the hosted complement: frontier reasoning or very long context goes through the Gateway; once verified, Baseten direct takes over.

Next: finish the Baseten workspace verification so direct routing replaces the Gateway fallback, and update the prompt set file with the Inkling trial results. See the running notes in ~/llm-lab/session-log.md for the live measurements.

── more in #large-language-models 4 stories · sorted by recency
── more on @thinking machines 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/sampling-inkling-and…] indexed:0 read:3min 2026-08-02 ·