Meet POCKET-27B. Qwen3.8-27B in ARCHsloth Q6_K GGUF. Choose files & download · Quality & limits

🏆 SuperCLUE November 2026: #1 open-weight model in math and science reasoning

From the VIDRAFT Darwin family. Our flagship reasoning model, Darwin-180B-RSI-R3, was scored by SuperCLUE, China's most widely cited LLM benchmark, on its private November 2026 test set: 73.68 in mathematical and scientific reasoning, #1 among open-weight models and #2 overall among 19 models, behind only OpenAI's GPT-6.1-Sol and ahead of Gemini-4-Argon, DeepSeek-V4.1-Flash, Grok-4.7 and Qwen3.8-Max. The same recursive self-improvement line and the same team built the POCKET on-device builds.

Darwin-180B-RSI inherited its expert layers from Qwen3.8-Flash-Next and rebuilt only the attention and shared-expert layers through recursive self-improvement. On the same board the parent, Qwen3.8-Flash, placed 15th overall (39.81) with 57.89 in math and science reasoning; Darwin placed 9th (43.08) with 73.68.

Overall intelligence index, November 2026 (screenshot)

Source: SuperCLUE general leaderboard, November 2026 (screenshots taken November 5, 2026). Scores are SuperCLUE's, not VIDRAFT's.

POCKET-35B-GGUF

Korean-tuned 35B local AI for PCs: choose a full-model GGUF build and run without a GPU.

Download files · Setup guide · Benchmarks

POCKET-35B · POCKET-26B · POCKET-Darwin-180B

At a glance

This repository contains the full-model PC builds, not the approximately 5 GB phone derivatives. For a phone, use the separate Korean GGUF, Korean MLX, or English GGUF repository and its own requirements.

Choose your build

File sizes are rounded decimal GB, not process-memory measurements. Context, runtime buffers, the operating system and other applications need additional memory. The approximately 8.2 GB IQ1_M file is approximately 7.7 GiB; do not interpret those units as different builds.

Download and run

Install the Hugging Face CLI and a llama.cpp build that supports qwen35moe. The example downloads only the recommended file from the audited revision; it does not clone or download the whole repository.

1. Download the recommended build.

hf download FINAL-Bench/POCKET-35B-GGUF POCKET-35B-Q2_K.gguf --revision 3870039a87406fb90764b27e3984c8b1a36b269e --local-dir ./POCKET-35B

2. Run on the CPU.

llama-cli -m ./POCKET-35B/POCKET-35B-Q2_K.gguf --device none -ngl 0 -t 8 -c 4096 -n 256 -p "Explain why local AI can be useful."

The expected result is generated text in the terminal, not a fixed benchmark answer. These command examples were syntax-reviewed but not executed during this review.

Commands use the standalone llama.cpp executable names. Some distributions expose a unified llama launcher; consult that distribution's help and the official model-loading documentation. For -t, start with the physical-core count rather than all logical threads; more threads can reduce throughput.

For installation, memory errors and app-specific help, use the model-specific setup guide. Model files remain directly available from Hugging Face without a VIDRAFT login.

Runtime compatibility

The same file format does not guarantee support in every app or version. A dated, exact-version compatibility matrix remains a community contribution opportunity.

Hardware and performance

These are publisher-reported measurements, not promised speeds for arbitrary PCs. The CPU-only quickstart explicitly disables GPU acceleration with --device none; -ngl 0 alone is not the strongest no-GPU guarantee in every backend.

On the 18 GB M3 Pro, the original card recommends Q2_K on CPU because its approximately 13 GB file exceeds the recommended Metal memory budget. This is a device-specific recommendation, not a universal Apple-memory limit.

Same-machine Bonsai comparison and benchmark command

The configurations do not establish equal quality, equal file size or a universal architecture advantage. The original card separately reports that Ternary-Bonsai-27B-Q2_0 required a PrismML fork; compatibility can change with releases.

To inspect the original CPU benchmark shape, first download IQ1_M instead of Q2_K, then run:

hf download FINAL-Bench/POCKET-35B-GGUF POCKET-35B-IQ1_M.gguf --revision 3870039a87406fb90764b27e3984c8b1a36b269e --local-dir ./POCKET-35B
llama-bench -m ./POCKET-35B/POCKET-35B-IQ1_M.gguf -p 128 -n 64 --device none -ngl 0 -t 16

This is a reproduction starting point, not proof of the published result on a different computer or runtime.

Quality and evaluation

Publisher-reported results. Each table has its own task, model and measurement conditions.

The Qwen3.6 reference is not a same-checkpoint Darwin BF16 baseline. Do not interpret its difference as quantization-only loss. Small benchmark subsets and overlapping confidence intervals do not establish general quality equivalence.

Lineage and language-specific derivatives

POCKET is quantized from Darwin-36B-Opus, VIDRAFT's multi-generation Darwin model. The original card describes a Qwen3.5-family sparse MoE architecture with 256 experts and top-8 routing; the distinct Qwen3.6 model above is an evaluation reference, not a replacement starting-checkpoint declaration.

The original card reports stronger Korean degradation at extreme precision and different Korean/English phone trade-offs. Do not transfer a language-specific derivative's quality or memory results to the full-model files in this repository.

Intended uses

• Local text assistance, experimentation and Korean-language workflows on a PC with suitable memory.
• Comparing quantization size, Korean perplexity and throughput on a clearly identified device.
• CPU-only workflows where local execution is preferred; no cloud service is required by the supplied command.

Limitations

• The smallest file in this repository is about 8.2 GB, not a 5 GB phone build.
• IQ1_M trades quality for size; Q2_K or a larger build is preferable when quality matters.
• MacBook M3 Pro measurements are supplied above. iPhone and Strix Halo throughput remain unmeasured in the supplied evidence.
• File size is not a complete RAM budget; longer context increases memory requirements.
• Published speed and benchmark results are device-, build-, quant- and protocol-specific, not universal guarantees.

License and attribution

This model card declares Apache-2.0, consistent with the current immediate starting checkpoint. Read the Apache-2.0 license and the starting checkpoint's license before redistribution.

Starting checkpoint: FINAL-Bench/Darwin-36B-Opus. POCKET quantization, language tuning and documentation: VIDRAFT / FINAL-Bench. Runtime tooling: the llama.cpp contributors. Keep required notices and attribution when redistributing.

Support and updates

For device selection and installation help, visit the VIDRAFT POCKET setup guide. Report reproducible issues in the model discussions, including the filename, runtime version, device, memory and command; do not post private prompts or credentials.

A browser-accessible POCKET-35B CPU demo is a separate hosted service; its availability and latency are not local-device measurements. No local-inference telemetry or website gate is required to obtain these public files.

POCKET family

Explore the POCKET collection. For phone-oriented derivatives, see KR GGUF, KR MLX and EN GGUF.

More POCKET projects and research

Qwen3.8 Flash-Next GGUF is a separate parent-model package, distinct from the POCKET-Darwin-180B RSI-R3 weights. Image projects are also separate: POCKET-Image-Zimage, POCKET-Zimage-CPU and Image Studio.

Research collections: Darwin, Aether, VKAE.

References

• Source card and publisher measurements, revision 3870039.
• Hugging Face CLI download documentation.
• llama.cpp build and CPU-backend guidance.
• llama.cpp model loading.
• Hugging Face with Ollama and LM Studio.
• VIDRAFT: on-device LLMs without a GPU and model quantization.

Documentation reviewed on 2026-11-04.