# HyperQwen > HyperQwen is syv.ai's open-source serving setup for Qwen3.8-27B on one 24 GB NVIDIA GPU. A patch series against a pinned vLLM, a requantisation pipeline and Docker Compose profiles run vLLM's OpenAI-compatible API on port 18020. - Canonical: https://www.anchorterminal.com/tools/hyperqwen - Pricing: https://www.anchorterminal.com/tools/hyperqwen#pricing - Reviews: https://www.anchorterminal.com/tools/hyperqwen#reviews - Markdown: https://www.anchorterminal.com/tools/hyperqwen.md (~8,200 tokens) - Slim: https://www.anchorterminal.com/tools/hyperqwen.min.md (~1,630 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/hyperqwen.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key) - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) - Updated: 2026-10-30 ## Overview **Grade C · 56.9/100 · rank #738 of 1239 · #11 in Local AI · not agent-ready · confidence medium** ## Assessment HyperQwen packages a patched vLLM 0.32.0 and requantised Qwen3.8-27B weights into one container with tool calling preset and a loopback bind when no key is set. It runs one model family, its speed figures come from one RTX 3090, and it has no versioned releases, changelog or security policy. ## Facts | Field | Value | | --- | --- | | Vendor | syv.ai (syv-ai on GitHub) (https://syv.ai) | | Kind | HTTP API | | Category | Local AI (https://www.anchorterminal.com/categories/local-ai) | | Transport | HTTP | | Auth | None · No credential by default. `VLLM_API_KEY` in `.env` (or an `api_key.txt` file) turns on vLLM's Bearer check. With no key, the launcher binds 127.0.0.1 outside a container, and Docker Compose publishes the port on 127.0.0.1 unless `BIND` is changed. With a key set, the launcher binds every interface. The key is vLLM's own, one static key with no scopes, which vLLM checks only under `/v1`, `/v2`, `/inference` and `/cohere` (per the vLLM listing's check of 9 October 2026, https://github.com/vllm-project/vllm/blob/main/docs/usage/security.md). | | Pricing | Free (Free · OSS) · Free under Apache-2.0 with no account, key or card. Nothing is sold. The README links a Ko-fi page for donations towards GPU time. The owner pays for a 24 GB NVIDIA GPU, about 40 GB of disk and electricity. | | x402 | No · No x402, MPP or L402 in the README, the docs or the launch scripts (checked 2026-10-30). Nothing is sold. | | Licence | Apache-2.0 | | Packages | oci: `ghcr.io/syv-ai/hyperqwen` | | Source | https://github.com/syv-ai/HyperQwen | | Docs | https://github.com/syv-ai/HyperQwen#readme | | llms.txt | not found | | GitHub stars | 2,400 (as of 2026-10-30) | | Surface listed | The HyperQwen repository at main on 30 October 2026 (README, docs, PATCHES.md, Dockerfile, docker-compose.yml, .env.example, the launchers and the CI workflows), read from raw.githubusercontent.com. Nothing was installed or run | | Interfaces | vLLM 0.32.0's OpenAI-compatible HTTP server on port 18020 (`/v1`, `/health`, `/metrics`), served model name `qwen3.8-27b`. Docker Compose profiles `single`, `batch`, `solo` and `prepare`, or a bare-metal venv install. No MCP server and no SDK of its own | | Setups | A batch (about 1,035 tokens a second aggregate at 64 concurrent), B single-user default (127 a second, 64k context), C reproduction (381 a second while quoting, 56k), D long context (150k, about 95 to 100 a second), E huge context (240k, 67 a second mixed). Project figures on one RTX 3090 at 250 W | | Model files | dbirks/Qwen3.8-27B-W4A16-AutoRound (about 19.5 GB) with lm_head, embeddings and the MTP module requantised to int8 in place, plus syvai/qwen3.8-27b-3090-fast-variant and syvai/Qwen3.8-27B-DFlash2-W4A16 (about 1 GB each), all Apache-2.0. Qwen/Qwen3.8-27B is the base model | | Hardware | A 24 GB Ampere or newer NVIDIA GPU, a CUDA 13 driver (580 or later), about 40 GB of disk. Volta and older can't run it. Measured on compute capability 8.6, with community runs on sm80, sm89 and sm120 and at TP=2 and TP=4 | | Tool calling | `--enable-auto-tool-choice --tool-call-parser qwen3_coder --tool-strict-level parameter` by default (`TOOLS=1`), `--reasoning-parser qwen3`, and a source build of xgrammar for bounded strings in tool schemas | | Network | Downloads from Hugging Face on first start and the image pull from ghcr.io. The Docker image turns off vLLM's usage statistics. The venv launchers leave vLLM's default on | | CI | Two GitHub workflows, `patch integrity` (about 40 GPU-less checks) and `docker image` (builds, applies every patch, runs build-time tests, pushes `latest` and `sha-<7>`, rebuilds weekly). Both badges read passing on 30 October 2026 | | Repository activity | 646 commits, 31 contributors, 0 open and 146 closed issues, 1 open and 276 closed pull requests, per shields.io on 30 October 2026. No tags, releases or CHANGELOG | | Capabilities | inference.local, inference.open-weights | | Tags | open-source, local, self-hosted, free, no-card, apache-2.0, openai-compatible, docker, tool-calling, reasoning, pre-1.0 | | JSON | https://www.anchorterminal.com/api/v1/tools/hyperqwen.json | ## Score breakdown (methodology v0.7, October 2026 research run) Assessed 2026-10-30 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 59 | 11.8 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 56 | 9.1 | | Agent ergonomics | 13% | 16.2 | 65 | 10.6 | | Security & auth | 14% | 17.5 | 41 | 7.2 | | Payments & pricing | 10% | 12.5 | 60 | 7.5 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 68 | 6.0 | | Transparency & trust (editorial 60, provenance 49) | 7% | 8.8 | 55 | 4.8 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **56.9 → C** | ### Why each score - Reliability 59 (checked 2026-10-30): Read with the local-software lines, since HyperQwen runs on the owner's GPU with no hosted service. A prebuilt image on ghcr.io with an immutable tag per commit, and a venv route, with the GPU, driver, Python and disk needs stated and Volta ruled out. The Compose route still needs a clone of the repository, and first start downloads an unpinned third-party checkpoint (18 of 20). Two GitHub workflows run about 40 GPU-less checks, and the image build applies every patch and runs the build-time tests. Both badges read passing on 30 October 2026 per shields.io. Nothing in CI runs on a GPU, where the serving path runs (20 of 25). shields.io counts 0 open and 146 closed issues and 1 open pull request. The README itself still describes an open speculation fault on sm80 cards (#98, #72), and the threads weren't read because github.com wasn't fetched (18 of 25). No tags, releases or changelog. The per-pin notes (docs/vllm-0.29.md to vllm-0.32.md) and PATCHES.md record what changed with each vLLM upgrade (3 of 15). No version number and nothing declared stable (0). - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 56 (checked 2026-10-30): Read with the API lines, for the local server an agent calls, which is vLLM 0.32.0's OpenAI-compatible server. vLLM's FastAPI app serves its own OpenAPI document at runtime. HyperQwen publishes none and documents only the base URL and the served model name (12 of 25). No llms.txt. The docs are Markdown files in the repository, readable raw (5 of 10). The README's decision tree and the knob tables say which setup suits which workload and when not to use one (for example `CTX=huge` only when the request wouldn't otherwise fit, `SPEC_ATTN=0` past 64k). The routes themselves are left to vLLM's docs (14 of 20). vLLM's typed request models, tool argument schemas enforced by default (`TOOL_STRICT=parameter`), and launchers that refuse invalid knob values before boot (11 of 15). An OpenCode client config, benchmark commands and a 64-item gotchas file with failure signatures such as the 400 for `tool_choice: auto` without a parser. No curl example and no error reference (9 of 15). No versions or changelog, a fixed `/v1` prefix and model name, and PATCHES.md with an upstream reference for every patch (5 of 15). - Agent ergonomics 65 (checked 2026-10-30): Read with the API lines. `max_tokens`, structured outputs, a reasoning parser that separates thinking from the answer, and a template step that maps OpenAI `reasoning_effort` values the model's template doesn't know. Context is 65,536 tokens by default, 131,072 or 245,760 in the long setups (18 of 25). No list routes worth paging, `/metrics` always and per-request timing with `REQ_METRICS=1`, and cached prompt tokens reported on every request (12 of 20). OpenAI-shaped errors from vLLM. The launcher's own refusals print a reason, and the gotchas file pairs error messages with fixes, with no list of codes (12 of 20). Generation is stateless and safe to repeat, and an SSE keep-alive patch keeps long prefills from tripping proxy timeouts. No retry guidance found (11 of 20). One `docker compose up` with tool calling, the right parser for this model and a loopback bind preset, and OpenAI clients work unchanged. First start can exceed 30 minutes and there is no SDK of its own (12 of 15). - Security & auth 41 (checked 2026-10-30): Read with the tool checklist. vLLM's optional static key, set by `VLLM_API_KEY` or `api_key.txt`, with no scopes and checked only under `/v1`, `/v2`, `/inference` and `/cohere` (per the vLLM listing's check of 9 October 2026). HyperQwen's launcher binds 127.0.0.1 when no key is set, Compose publishes on 127.0.0.1 by default, a CI check tests the no-key bind, and `.env.example` says the key is required before exposing the port (15 of 30). Inference only, but vLLM's control routes such as `/pause` answer without the key, and the container runs as root (6 of 20). The server returns model output and fetches no outside content with the default `VISION=0`. No prompt-injection guidance (9 of 15). vLLM's access logs and Prometheus `/metrics`, with optional per-request timing, and no per-key record (8 of 15). No SECURITY.md, disclosure address or advisories, and no security.txt on syv.ai. The image is rebuilt weekly for base-image fixes, but the base weights come from a third-party repository (dbirks/Qwen3.8-27B-W4A16-AutoRound) downloaded with no pinned revision or checksum of the project's own (3 of 20). - Payments & pricing 60 (checked 2026-10-30): Read with the self-hosted rule. No x402, MPP or L402, and nothing is sold. The Ko-fi link takes donations and buys nothing (0). Free under Apache-2.0 with no account, key or card, so 20, 20 and 20 on the last three lines. - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 68 (checked 2026-10-30): No versioned release. Every push to main that touches code publishes `latest` and an immutable `sha-<7>` image from CI, and shields.io reports the last commit on 30 October 2026 (25 of 30). No releases or dated changelog entries. Four vLLM pins (0.29.0 to 0.32.0) have dated upgrade notes since August, and shields.io counts 207 commits in the last month (10 of 20). 0 open of 146 issues, 1 open of 277 pull requests and 31 contributors, with community field reports written into docs/reproductions with credit. Reply times weren't read (20 of 25). Not an MCP server and no SDK of its own. OpenAI clients work against it (5 of 15). Pinned to vLLM 0.32.0 with the CUDA compiler set pinned to match, a weekly image rebuild and CI that fails when PATCHES.md is out of date (8 of 10). - Transparency & trust 55 (checked 2026-10-30): The editorial half. Apache-2.0 for the repository, the vendored pth-flash-attn source and the fa2 plugin (with FlashAttention's BSD-3-Clause notices kept), and Apache-2.0 on the base model and every checkpoint it downloads (30). No privacy or data statement for the software. The Docker image turns off vLLM's usage statistics, but the venv launchers don't, and nothing in the README or docs says so. Outbound calls are downloads from Hugging Face and ghcr.io (12 of 30). PATCHES.md says what retires each patch, and upgrade notes say what changed per vLLM pin. Knobs and setups change without a deprecation notice or dates (8 of 20). The telemetry switch is set in the Dockerfile and not documented for venv installs, which inherit vLLM's default (10 of 20). Fix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (18 items): https://www.anchorterminal.com/fixes/hyperqwen.md (JSON https://www.anchorterminal.com/fixes/hyperqwen.json) ### What we couldn't check - The lead matched. HyperQwen is runnable software (Compose profiles, a prebuilt image, 60 vLLM patches, launchers and CI), not only a benchmark write-up. - firstReleased is 18 August 2026, the first commit of the companion Hugging Face files that name the repository under its earlier name, syv-ai/qwen38-27b-rtx3090, and the date of the earliest batch measurement in batch/README.md. shields.io gives only the creation month, August 2026. The date of the rename to HyperQwen wasn't established first-hand. - unchecked: github.com and api.github.com. Our proxy refused api.github.com for this repository and github.com/robots.txt couldn't be read, so github.com wasn't fetched. Repository counts and CI status come from shields.io, files from raw.githubusercontent.com. Issue threads, reply times and the contributor list weren't read. - The headline figures (127 tokens a second for one stream, about 1,035 aggregate at 64 concurrent) are the project's claims. The community reproductions in docs/reproductions come from GitHub issues we didn't read. The AlphaSignal item repeats the README. - Whether vLLM 0.32.0 carries the fixes for the vLLM advisories recorded on the vllm listing (including GHSA-h3rc-6mm3-gc2m of 6 October 2026) wasn't checked. - Who maintains HyperQwen at syv.ai isn't stated first-hand. The README's Ko-fi link is ko-fi.com/mhenrichsen, the handle of syv.ai's founder Mads Henrichsen, and ko-fi.com wasn't read. ### Sources - README (setups, headline figures, roadmap, field tests): (seen 2026-10-30) - PATCHES.md (60 patches against vLLM 0.32.0): (seen 2026-10-30) - docker-compose.yml (profiles, 127.0.0.1 publish, healthcheck): (seen 2026-10-30) - .env.example (key and BIND guidance): (seen 2026-10-30) - Dockerfile (vLLM 0.32.0, build-time tests, usage statistics off): (seen 2026-10-30) - single-user launcher (served model name, tool parser, strict level): (seen 2026-10-30) - bind-host and key resolution: (seen 2026-10-30) - key resolver: (seen 2026-10-30) - model preparation run on every container start: (seen 2026-10-30) - CI workflow, patch integrity: (seen 2026-10-30) - CI workflow, docker image: (seen 2026-10-30) - bare-metal install: (seen 2026-10-30) - Docker and WSL2 notes: (seen 2026-10-30) - client configuration: (seen 2026-10-30) - benchmarks and comparison with ninfer-3090: (seen 2026-10-30) - quality per configuration: (seen 2026-10-30) - community reproductions: (seen 2026-10-30) - repository counts (stars, issues, pull requests, contributors, commits, CI status, created month): (seen 2026-10-30) - companion fast-variant files, first commit 18 August 2026: (seen 2026-10-30) - base W4A16 checkpoint metadata: (seen 2026-10-30) - Qwen3.8-27B model metadata (Apache-2.0, created 5 August 2026): (seen 2026-10-30) - syv.ai organisation on Hugging Face (links syv.ai and github.com/syv-ai): (seen 2026-10-30) - syv.ai contact page (address, CVR): (seen 2026-10-30) - AlphaSignal item indexed on hermes-ai.net, 19 September 2026 (press lead): (seen 2026-10-30) ## Score history Every move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/hyperqwen/history.json - 2026-10-30: graded 56.9 C (methodology 0.7) ## Who's behind it (provenance 49/100, checked 2026-10-30) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | syv.ai (Copenhagen, CVR DK44671247) | 20/20 | | Domain age | syv.ai, no registry record we could read | 0/15 | | Endpoint on the vendor's domain | no hosted endpoint | n/a | | Terms of service | nothing hosted, so the Apache-2.0 licence stands in | 10/10 | | Privacy policy | read, states 0 of the 8 things a reader expects | 4/10 | | Status page | not found | 0/10 | | Changelog | not found | 0/10 | | security.txt | not found | 0/10 | | People named | 2 named with their role, 2 with a public profile | 10/10 | | Support route | help pages, a community | 5/5 | The Hugging Face organisation syvai, full name syv.ai, links https://syv.ai and github.com/syv-ai, and hosts the drafter files HyperQwen downloads. syv.ai's own pages don't mention HyperQwen. syv.ai's contact page gives the address in Copenhagen and CVR DK44671247. The Danish CVR register answered with a bot check and wasn't read. No terms, SECURITY.md or changelog for HyperQwen. The Apache-2.0 licence stands in for terms. The privacy policy listed is syv.ai's website policy and doesn't cover the software, which runs on the owner's machine. syv.ai answers 404 at /.well-known/security.txt and /security.txt. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service**. Nothing is hosted by the vendor, so there are no terms of service to read. The Apache-2.0 licence stands in and the check scores in full. **Privacy policy** (https://syv.ai/privatlivspolitik), read 2026-10-30, gives no date, states 0 of the 8 things a reader expects. - Not found in the text. Gives the date it was last updated. - Not found in the text. Says what personal data is collected. - Not found in the text. Says how long data is kept. - Not found in the text. Says who else receives the data. - Not found in the text. Says whether personal data is sold or shared for advertising. - Not found in the text. Says what rights people have over their data. - Not found in the text. Gives a privacy contact. - Not found in the text. Says where data is transferred or stored. ## Humans behind the project (researched 2026-10-30 from public pages, not part of the grade) ### Key people - Mads Henrichsen, Founder and partner, syv.ai. LinkedIn: https://www.linkedin.com/in/mhenrichsen/. GitHub: https://github.com/mhenrichsen - Søren Søndergaard Poulsen, Partner, syv.ai. LinkedIn: https://www.linkedin.com/in/s%C3%B8ren-christian-s%C3%B8ndergaard-poulsen/ - Note: hyperqwen sits in the syv-ai github organisation. the hugging face organisation syvai, full name syv.ai, links https://syv.ai and github.com/syv-ai and hosts the drafter files hyperqwen downloads. syv.ai's team and contact pages (read 30 october 2026) name mads henrichsen as founder and partner and søren søndergaard poulsen as partner, with their linkedin links. the github link for mads henrichsen is the one on his own hugging face profile (mhenrichsen), which uploaded the syvai organisation's avatar. syv.ai's pages don't mention hyperqwen, and no first-hand page names its maintainers. the readme's donation link is ko-fi.com/mhenrichsen, which wasn't read. shields.io counts 31 contributors, whose names weren't read because github.com wasn't fetched. work email addresses and phone numbers on syv.ai are left out. no investors are listed. syv.ai's site and a web search found no funding round or named investor, and the danish cvr register answered with a bot check. - syv.ai: GitHub https://github.com/syv-ai ### Getting support - Help: https://github.com/syv-ai/HyperQwen/issues - Community (Field report issue form): https://github.com/syv-ai/HyperQwen/issues/new?template=field-report.yml - Sources: https://raw.githubusercontent.com/syv-ai/HyperQwen/main/README.md, https://syv.ai/team, https://syv.ai/kontakt, https://huggingface.co/syvai, https://huggingface.co/api/organizations/syvai/overview, https://huggingface.co/mhenrichsen, https://huggingface.co/api/users/mhenrichsen/overview ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Strengths - Prebuilt image on ghcr.io with an immutable tag per commit, built by CI that applies all 60 patches and runs the build-time tests - Tool calling on by default with the `qwen3_coder` parser and argument schemas enforced (`TOOL_STRICT=parameter`) - With no API key the server listens on 127.0.0.1 only, and a CI check tests that default - Five documented setups from 64k to 240k context, with the measured cost of each knob - Apache-2.0 throughout, with vendored kernels and patches carrying their upstream references ## Weaknesses - Serves Qwen3.8-27B and checkpoints derived from it only. Other models are on the roadmap - No tags, releases or changelog. Changes reach users through `latest` on every push to main - No SECURITY.md or disclosure route, and the base weights come from a third-party repository with no pinned revision - vLLM's key covers only `/v1`-style prefixes, so control routes such as `/pause` answer without it - First start pulls a 9.5 GB image and about 20 GB of weights and can take over 30 minutes ## Before you call it (notes for agents) 1. Call http://127.0.0.1:18020/v1 with model `qwen3.8-27b` and the `VLLM_API_KEY` value, or any string if no key was set 2. Poll `/health` before the first request. A first start downloads and prepares the model and compiles kernels, which can take over 30 minutes 3. Declare the context window your setup uses (65,536 by default, 131,072 for `CTX=long`, 245,760 for `CTX=huge`) so the client doesn't truncate 4. Ask the owner to set `VLLM_API_KEY` before setting `BIND=0.0.0.0`, and to front the port with a proxy that allowlists routes 5. Treat the README's tokens-per-second figures as the project's measurements on one RTX 3090 at 250 W ## Connect Install: ```bash git clone https://github.com/syv-ai/HyperQwen && cd HyperQwen cp .env.example .env docker compose --profile single up -d # one or a few people chatting docker compose --profile batch up -d # API backend, many concurrent requests ``` Through letme: https://letme.dev/hyperqwen. letme answers with the pick and how to call it direct. How it works: https://www.anchorterminal.com/letme/index.md ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | LocalAI | B | 68.5 | 240 | inference.local, inference.open-weights | no | https://www.anchorterminal.com/tools/localai.md | | Lemonade | B | 63.9 | 430 | inference.local, inference.open-weights | no | https://www.anchorterminal.com/tools/lemonade.md | | KoboldCpp | C | 61 | 570 | inference.local, inference.open-weights | no | https://www.anchorterminal.com/tools/koboldcpp.md | | llama.cpp | C | 60.6 | 590 | inference.local, inference.open-weights | no | https://www.anchorterminal.com/tools/llama-cpp.md | | Foundry Local | C | 60.5 | 592 | inference.local, inference.open-weights | no | https://www.anchorterminal.com/tools/foundry-local.md | | Nemotron 3.5 Super VL | C | 58.8 | 666 | inference.open-weights, inference.local | no | https://www.anchorterminal.com/tools/nemotron-3-5-super-vl.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - The repository has no tags and no GitHub releases, and shields.io gives its creation month as August 2026. The companion Hugging Face repository syvai/qwen3.8-27b-3090-fast-variant was first committed on 18 August 2026 and names the project's earlier repository, syv-ai/qwen38-27b-rtx3090 (source: ) - The headline figures are the project's own, from one RTX 3090 capped at 250 W that the README says is shared with training jobs. 127 tokens a second for one stream, about 1,035 aggregate decode at 64 concurrent requests (128 in, 512 out) and 381 while an answer quotes its prompt (source: ) - docs/reproductions lists runs by other people on other hardware, taken from GitHub issues, such as 135.5 tokens a second for one stream on an RTX 4090 and 182.8 on two RTX 3090s at TP=2. These are relayed by the project and were not read at their source (source: ) - PATCHES.md lists 60 patches against vLLM 0.32.0 (27 fixes, 19 additions vLLM lacks, 6 local changes, 5 fixes to the project's own additions and 3 backports), with 10 marked upstreamed and 16 as open upstream pull requests (source: ) - The base weights are a third-party W4A16 quantisation, dbirks/Qwen3.8-27B-W4A16-AutoRound (created 14 August 2026), which docker/prepare.sh downloads with no pinned revision and then rewrites in place (source: ) - The Docker image sets `VLLM_NO_USAGE_STATS=1` and `DO_NOT_TRACK=1`. The bare-metal launchers set neither, so a venv install keeps vLLM's default usage statistics (source: ) - An AlphaSignal item indexed on hermes-ai.net on 19 September 2026 used the HyperQwen name and repeated the README's figures. It is a press lead, not a measurement (source: ) - #11 of 23 in Best local AI models and assistants: https://www.anchorterminal.com/best/local-ai/index.md - All 253 local ai comparisons: https://www.anchorterminal.com/compare/local-ai/index.md ## Compare - [AnythingLLM vs HyperQwen](https://www.anchorterminal.com/compare/anythingllm-vs-hyperqwen.md): D 53.5 vs C 56.9 - [Berth vs HyperQwen](https://www.anchorterminal.com/compare/berth-vs-hyperqwen.md): B 67.6 vs C 56.9 - [BitRun vs HyperQwen](https://www.anchorterminal.com/compare/bitrun-vs-hyperqwen.md): E 38.3 vs C 56.9 - [Docker Model Runner vs HyperQwen](https://www.anchorterminal.com/compare/docker-model-runner-vs-hyperqwen.md): C 57.2 vs C 56.9 - [Foundry Local vs HyperQwen](https://www.anchorterminal.com/compare/foundry-local-vs-hyperqwen.md): C 60.5 vs C 56.9 - [Core vs HyperQwen](https://www.anchorterminal.com/compare/ghost-core-vs-hyperqwen.md): F 7.4 vs C 56.9 - [GPT4All vs HyperQwen](https://www.anchorterminal.com/compare/gpt4all-vs-hyperqwen.md): F 36.4 vs C 56.9 - [HyperQwen vs Jan](https://www.anchorterminal.com/compare/hyperqwen-vs-jan.md): C 56.9 vs D 51.4 - [HyperQwen vs Khoj](https://www.anchorterminal.com/compare/hyperqwen-vs-khoj.md): C 56.9 vs E 38.8 - [HyperQwen vs KoboldCpp](https://www.anchorterminal.com/compare/hyperqwen-vs-koboldcpp.md): C 56.9 vs C 61 - [HyperQwen vs Lemonade](https://www.anchorterminal.com/compare/hyperqwen-vs-lemonade.md): C 56.9 vs B 63.9 - [HyperQwen vs llama.cpp](https://www.anchorterminal.com/compare/hyperqwen-vs-llama-cpp.md): C 56.9 vs C 60.6 - [HyperQwen vs LM Studio](https://www.anchorterminal.com/compare/hyperqwen-vs-lm-studio.md): C 56.9 vs C 58.1 - [HyperQwen vs LocalAI](https://www.anchorterminal.com/compare/hyperqwen-vs-localai.md): C 56.9 vs B 68.5 - [HyperQwen vs MLX LM](https://www.anchorterminal.com/compare/hyperqwen-vs-mlx-lm.md): C 56.9 vs D 52.5 - [HyperQwen vs Ollama](https://www.anchorterminal.com/compare/hyperqwen-vs-ollama.md): C 56.9 vs C 56.6 - [HyperQwen vs Open WebUI](https://www.anchorterminal.com/compare/hyperqwen-vs-open-webui.md): C 56.9 vs D 52 - [HyperQwen vs screenpipe](https://www.anchorterminal.com/compare/hyperqwen-vs-screenpipe.md): C 56.9 vs C 61 - [HyperQwen vs TextGen](https://www.anchorterminal.com/compare/hyperqwen-vs-text-generation-webui.md): C 56.9 vs E 45.7 - [HyperQwen vs vLLM](https://www.anchorterminal.com/compare/hyperqwen-vs-vllm.md): C 56.9 vs C 58 - [HyperQwen vs Underdog](https://www.anchorterminal.com/compare/hyperqwen-vs-underdog.md): C 56.9 vs F 30.1 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on syv.ai or one of its subdomains, or the README of github.com/syv-ai/HyperQwen. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "hyperqwen", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html HyperQwen on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![HyperQwen on Anchor Terminal](https://www.anchorterminal.com/badges/hyperqwen.svg)](https://www.anchorterminal.com/tools/hyperqwen) ``` Plain link: ```html HyperQwen on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say HyperQwen is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/hyperqwen-dark.png - Light: https://www.anchorterminal.com/assets/share/hyperqwen-light.png - Create a video and download its frames: https://www.anchorterminal.com/assets/listing-video/index.html?listing=hyperqwen --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp