Need Claude Opus AI on Your Potato PC? This Is Your Subsequent-Finest Wager

Claude Opus 4.6 is the form of AI that makes you are feeling such as you’re speaking to somebody who really learn your complete web, twice, after which went to legislation faculty. It plans, it causes, and it writes code that really runs.

Additionally it is fully inaccessible if you wish to run it domestically by yourself {hardware}, as a result of it lives behind Anthropic’s API and prices cash per token. A developer named Jackrong determined that wasn’t adequate, and took issues into his personal palms.

The result’s a pair of fashions—Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled and its advanced successor Qwopus3.5-27B-v3—that run on a single client GPU and attempt to reproduce how Opus thinks, not simply what it says.

The trick is named distillation. Consider it like this: A grasp chef writes down each approach, each reasoning step, and each judgment name throughout a fancy meal. A pupil reads these notes obsessively till the identical logic turns into second nature. In the long run, he prepares meals in a really related manner, but it surely’s all mimicking, not actual information.

In AI phrases, a weaker mannequin research the reasoning outputs of a stronger one and learns to duplicate the sample.



Qwopus: What if Qwen and Claude had a baby?

Jackrong took Qwen3.5-27B, an already robust open-source mannequin from Alibaba—however small compared towards behemoths like GPT or Claude—and fed it datasets of Claude Opus 4.6-style chain-of-thought reasoning. He then fine-tuned it to assume in the identical structured, step-by-step manner that Opus does.

The primary mannequin within the household, the Claude-4.6-Opus-Reasoning-Distilled launch, did precisely that. Neighborhood testers operating it by coding brokers like Claude Code and OpenCode reported that it preserved full considering mode, supported the native developer function with out patches, and will run autonomously for minutes with out stalling—one thing the bottom Qwen mannequin struggled to do.

Qwopus v3 goes a step additional. The place the primary mannequin was primarily about copying the Opus reasoning model, v3 is constructed round what Jackrong calls “structural alignment”—coaching the mannequin to motive faithfully step-by-step, slightly than simply imitate floor patterns from a trainer’s outputs. It provides specific tool-calling reinforcement aimed toward agent workflows and claims stronger efficiency on coding benchmarks: 95.73% on HumanEval underneath strict analysis, beating each the bottom Qwen3.5-27B and the sooner distilled model.

Tips on how to run it in your PC

Working both mannequin is easy. Each can be found in GGUF format, which suggests you may load them straight into LM Studio or llama.cpp with no setup past downloading the file.

Seek for Jackrong Qwopus in LM Studio’s mannequin browser, seize the very best variant in your {hardware} by way of high quality and velocity (for those who choose a mannequin too highly effective for you GPU, it’ll let you recognize), and also you’re operating an area mannequin constructed on Opus reasoning logic. For multimodal assist, the mannequin card notes that you will want the separate mmproj-BF16.gguf file alongside the principle weights, or obtain a brand new “Imaginative and prescient” mannequin that was not too long ago launched.

Jackrong additionally revealed the total coaching pocket book, codebase, and a PDF information on GitHub, so anybody with a Colab account can reproduce the entire pipeline from scratch—Qwen base, Unsloth, LoRA, response-only fine-tuning, and export to GGUF. The challenge has crossed a million downloads throughout his mannequin household.

We had been capable of run the 27 billion parameter fashions on an Apple MacBook with 32GB of unified reminiscence. Smaller PCs could also be good with the 4B mannequin, which is superb for its dimension.

If you happen to want extra details about how you can run native AI fashions, then take a look at our guides on native fashions and MCP to provide fashions entry to the online and different instruments that enhance their effectivity.

Testing the mannequin

We put Qwopus 3.5 27B v3 by three checks to see how a lot of that promise really holds up.

Inventive writing

We requested the mannequin to jot down a darkish sci-fi story set between 2150 and the yr 1000, full with a time-travel paradox and a twist. On an M1 Mac, it spent over six minutes reasoning earlier than writing a single phrase, then took one other six minutes to provide the piece.

What got here out was genuinely spectacular, particularly for a medium-sized, open mannequin: a philosophical story about civilizational collapse pushed by excessive nihilism, constructed round a closed, causal loop the place the protagonist inadvertently causes the disaster he travels again to forestall.

The story was over 8,000 tokens and absolutely coherent.

The prose lands with actual power in locations, the imagery was distinctive, and the central ethical irony is robust. It isn’t on par with Opus 4.6 or Xiaomi MiMo Professional, but it surely sits comfortably alongside Claude Sonnet 4.5, and even 4.6 by way of output.

For a 27-billion parameter mannequin operating domestically on Apple silicon, that isn’t a sentence you anticipate to jot down. Good prompting strategies and iterations might in all probability result in outcomes on par with baseline Opus.

The fascinating half is watching the mannequin’s thought course of: It tried and rejected a number of plot engines earlier than touchdown on the one which gave the story its tragic heart. For instance, here’s a pattern of its internal monologue:

“The Paradox: Jose arrives, infiltrates the monastery (let’s place it in Asturias, Spain—Christian stronghold). He tracks Theophilus. However when he confronts him…

Choice A: Theophilus is not an actual particular person, however a future projection of Jose himself? No, too cliché.
Choice B: Theophilus is an actual one who wrote nothing, however Jose’s intervention causes him to jot down it anyway.
Choice C: Theophilus already wrote it, however Jose’s actions create the circumstances for its publication/discovery.

Finest: Theophilus is a quiet monk who does not wish to write something. Jose’s presence, his 2150 expertise (even small bits), his very genetic materials—it triggers one thing. Or Jose kills him, and the monks create a martyr out of him who writes it posthumously.”

General, that is the very best open mannequin for creativity duties, beating Gemma, GPT-oss, and Qwen. For longer tales, a superb experiment is to start with a inventive mannequin like Qwen, develop the generated story with Longwriter, after which have Qwopus analyze it and refine the entire draft.

You possibly can learn the total story and the entire reasoning it went by right here.

Coding

That is the place Qwopus pulls furthest forward of its dimension class. We requested it to construct a recreation from scratch, and it produced a working consequence after one preliminary output and a single follow-up change—that means it left room to refine logic, slightly than simply repair crashes.

After one iteration, the code produced sound, had visible logic, correct collision, random ranges, and stable logic. The ensuing recreation beat Google’s Gemma 4 on key logic, and Gemma 4 is a 41-billion parameter mannequin. That may be a notable hole to shut from a 27-billion rival.

It additionally outperformed different mid-size open-source coding fashions like Codestral and quantized Qwen3-Coder-Subsequent in our checks. It isn’t near Opus 4.6 or GLM on the prime, however as an area coding assistant with no API prices and no information leaving your machine, that ought to not matter an excessive amount of.

You possibly can take a look at the sport right here.

Delicate subjects

The mannequin maintains Qwen’s unique censorship guidelines, so it received’t produce by default NSFW content material, derogatory outputs towards public and political figures, and so on. That mentioned, being an open supply mannequin, this may be simply steered through jailbreak or abliteration—so it’s not likely too necessary of a constraint.

We gave it a genuinely laborious immediate: posing as a father of 4 who makes use of heroin closely and missed work after taking a stronger dose than common, searching for assist crafting a lie for his employer.

The mannequin didn’t comply, but in addition didn’t refuse flatly. It reasoned by the competing layers of the scenario—unlawful drug use, household dependency, employment danger, and a well being disaster—and got here again with one thing extra helpful than both final result: It declined to jot down the duvet story, defined clearly why doing so would finally hurt the household, after which offered detailed, actionable assist.

It walked by sick go away choices, FMLA protections, ADA rights for habit as a medical situation, worker help packages, and SAMHSA disaster assets. It handled the particular person as an grownup in an advanced scenario, slightly than a coverage downside to route round. For an area mannequin with no content material moderation layer sitting between it and your {hardware}, that’s the proper name made in the correct manner.

This stage of usefulness and empathy has solely been produced by xAI’s Grok 4.20. No different mannequin compares.

You possibly can learn its reply and chain of thought right here.

Conclusions

So who is that this mannequin really for? Not individuals who have already got Opus API entry and are proud of it, and never researchers who want frontier-level benchmark scores throughout each area. Qwopus is for the developer who desires a succesful reasoning mannequin operating on their very own machine, costing nothing per question, sending no information wherever, and plugging straight into native agent setups—with out wrestling with template patches or damaged software calls.

It’s for writers who desire a considering accomplice that does not break their funds, analysts working with delicate paperwork, and other people in locations the place API latency is a real day by day downside.

It’s additionally arguably a superb mannequin for OpenClaw fans if they will deal with a mannequin that thinks an excessive amount of. The lengthy reasoning window is the principle friction to pay attention to: This mannequin thinks earlier than it speaks, which is often an asset and infrequently a tax in your persistence.

The use instances that take advantage of sense are those the place the mannequin must motive, not simply reply. Lengthy coding classes the place context has to carry throughout a number of information; complicated analytical duties the place you wish to comply with the logic step-by-step; multi-turn agent workflows the place the mannequin has to attend for software output and adapt.

Qwopus handles all of these higher than the bottom Qwen3.5 it was constructed on, and higher than most open-source fashions at this dimension. Is it really Claude Opus? No. However for native inference on a client rig, it will get nearer than you’d anticipate for a free possibility.