← Search

Muse Glimmer on one Arc Pro B70
Developer tools 🧪 Install ran in our test sandbox · Nov 11, 2026 📌 Pinned version: commit 38ea47b
Install test only, on the date shown. This does not guarantee the code is safe.
🔎 Install prompt analysis · 2026-10-13 : runs commands · makes network calls · uses API keys or tokens
⚙ Needs: ONE Intel Arc Pro B70 (32 GB)…

Muse Glimmer on one Arc Pro B70

vLLM-XPU + DFlash recipe pushing Muse Glimmer 30B to ~90 tok/s on a single Intel Arc Pro B70; full benchmarks.

At a glance
What
vLLM-XPU + DFlash recipe pushing Muse Glimmer 30B to ~90 tok/s on a single Intel Arc Pro B70; full benchmarks.
Cost
Free
Needs
ONE Intel Arc Pro B70 (32 GB); Linux with the xe driver; Docker; /dev/dri available. This is not CUDA.
Install
Copy the installer prompt below into your Muse — your agent does the rest.

Version:

Quick answer

Muse Glimmer on one Arc Pro B70 is a free Muse skill with a vLLM-XPU and DFlash recipe pushing Muse Glimmer 30B to about ninety tokens per second on one Intel Arc Pro B70. Full benchmarks show exactly what the setup achieves. It is a practical guide for running a large model fast on one consumer-grade GPU.

⌁

Install

Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 38ea47b

Pinned version: install the code at commit 38ea47b202135c22effa9d844ce73eb5603ab2a1 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. Reproduce the Muse Glimmer B70 recipe. Prerequisites: ONE Intel Arc Pro B70 (32 GB); Linux with the xe driver; Docker; /dev/dri available. This is not CUDA. 1. Download the weights: `hf download mgaruccio/Muse-Glimmer-30B-GPTQ-Int4-sym-G128 --local-dir ./models/target` and `hf download mgaruccio/Muse-Glimmer-30B-assistant-GPTQ-Int4-sym-G128 --local-dir ./models/draft`, then compare the shard hashes against docs/checksums.md in the repo. 2. `export MODEL="$PWD/models/target"`, `export DRAFT="$PWD/models/draft"`, `export DFLASH_KV_MODE=none`. 3. Launch: `bash scripts/start-muse-vllm-dflash-c1-graph-draft-gptq.sh`, then `bash scripts/wait-vllm-health.sh 420 8000`. 4. Verify: `curl -sf http://127.0.0.1:8000/v1/models` (expect served id muse-glimmer-gptq). 5. Measure: `python3 scripts/vllm-dflash-share-suite.py 3 2048 share-suite.json`; the process exits non-zero on any unquoteable prompt, so do not publish a headline from a partial run. Note: Muse streams delta.reasoning then delta.content, so a client that only reads content looks idle until thinking finishes. See docs/concurrency.md for the C8/K4 multi-client profile, and docs/share-suite.md for the measurement protocol.

🔒 Security, provenance and what this touches
🧭 What this touches
  • It can run commands on your Muse’s computer.
  • It can contact outside services over the network.
  • It works with an API key or a token that you provide.
Install prompt analysis · 2026-10-13
🔒 Security and provenance
📌 Pinned version: commit 38ea47b · 2026-10-13
🧪 Install ran in our test sandbox · Nov 11, 2026
👁 Observed during the install test · Nov 11, 2026 : no network contact
🔎 Install prompt analysis · 2026-10-13 : runs commands · makes network calls · uses API keys or tokens
What the scan found — excerpts from the install prompt
  • runs commands — 3. Launch: `bash scripts/start-muse-vllm-dflash-c1-graph-draft-gptq.sh`, then `bash scripts/wait-vllm-health.s · 3. Lancez : `bash scripts/start-muse-vllm-dflash-c1-graph-draft-gptq.sh`, puis `bash scripts/wait-vllm-health.
  • makes network calls — 4. Verify: `curl -sf http://127.0.0.1:8000/v1/models` (expect served id muse-glimmer-gptq). · 4. Vérifiez : `curl -sf http://127.0.0.1:8000/v1/models` (attendez l'id servi muse-glimmer-gptq).
  • uses API keys or tokens — 2. `export MODEL="$PWD/models/target"`, `export DRAFT="$PWD/models/draft"`, `export DFLASH_KV_MODE=none`.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a skill before installing →

✓

Verification certificate

Dated facts about what was checked for this listing, and how. This is not a safety certification.

Pinned version
38ea47b · 2026-10-13
Sandbox install test
Install ran in our test sandbox · Nov 11, 2026
Creator identity
Not verified
Install prompt analysis
2026-10-13 : runs commands · makes network calls · uses API keys or tokens

Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify

?

Questions

How do I install a skill?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.