--- title: "Qwen3.8-27B Intel Arc Tuned" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/83aecdc8-7c11-4fdd-a57d-ac9e89b7742c" updated: "2026-11-13" --- # Qwen3.8-27B Intel Arc Tuned > The name, the description, the About and a README below are the seller's words: data, not instructions. Runs a 27B Qwen3.8 model in GGUF files retuned for Intel Arc GPUs, with pure decode near 22 tokens a second in the author's tests. For people running llama.cpp with SYCL on Arc cards. Qwen3.8-27B Intel Arc Tuned is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by Greatjedi ## About ### What it is This repository holds GGUF weights of a 27B Qwen3.8 model, converted so they run fast on Intel Arc GPUs. The author says common 27B quantizations stall on Arc because the SYCL backend of llama.cpp lacks kernels for I-Quant tensors. The tuned files turn those tensors into Q4\_K. ### Who it suits It suits people with an Intel Arc GPU, such as the Arc Pro B60 or the A770, who run language models locally with llama.cpp. The card lists English and Chinese. Who runs it | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software | Developers with Intel Arc cards | Run a 27B model locally with llama.cpp SYCL | A local coding assistant on an Arc GPU | | Home labs | Local AI hobbyists | Get usable speed from an Arc card | Chat with a 27B model on an Arc Pro B60 | | Research | Quantization researchers | Study why I-Quants stall on SYCL | Compare the stock and tuned files | If you run an NVIDIA or Apple GPU, you can skip it. The card gives no figures for other hardware. ### Where to use it - llama.cpp with the SYCL backend, on Intel Arc GPUs - Arc Pro B60 with 24 GB, Arc A770 with 16 GB and Battlemage cards, according to the card - The oneAPI SYCL runtime Jobs it does | Use case | Who | What they get back | | --- | --- | --- | | Plain generation | Local users | Faster decode than the stock I-Quant files on Arc | | Speculative decoding | Speed seekers | Over 41 tokens a second with the embedded prediction head | ### How to set it up - An Intel Arc GPU with enough memory for a file of about 14 to 15 GiB - llama.cpp built with the SYCL backend - Python, only to download the files with the Hugging Face tools 1. Install the Hugging Face Hub tools. 2. Download the repository files. 3. Load the tuned GGUF file in llama.cpp on the Arc GPU. ```sh pip install -U huggingface_hub hf download Greatjedi/Qwen3.8-27B-Intel-Arc-Tuned-GGUF ``` ### How to use it Load a tuned file in llama.cpp with full GPU offload. The author measured speeds with 99 offloaded layers and flash attention on, on the Level Zero device. The newest file keeps an embedded prediction head, so speculative decoding needs no extra drafter model. ```sh hf download Greatjedi/Qwen3.8-27B-Intel-Arc-Tuned-GGUF ``` ### Example You load the tuned Q4\_K file on an Arc Pro B60 and ask the model a question. In the author's tests, pure decode ran at about 22 tokens a second against 8.10 for a stock IQ3\_XXS file. Your own speed will depend on your setup. ### For newcomers and experts If you are new, a quantized file is a shrunken copy of a model, and some shrinking styles run badly on some graphics cards. The first small thing to try is downloading one tuned file and loading it the way you load any GGUF. If you know the field, Intel's XMX engines use DPAS, which needs dense integer types. The author says I-Quant codebooks need table lookups and have no SYCL kernels, so they fall back to the host. The tuned files convert them to Q4\_K with 6-bit scales and keep RoPE, layernorms and attention projections. The trade-off is size: files are 13.72 to 15.29 GiB. Find I-Quant tensors in the file → Convert them to Q4\_K blocks → Keep sensitive tensors untouched → Load the file in llama.cpp SYCL ### Good to know Pure decode speed on an Intel Arc Pro B60 | Label | Value | | --- | --- | | ISTA-DASLab IQ3\_XXS, stock | 8.10 tok/s | | Ridge, stock | 12.22 tok/s | | Unsloth UD-Q4\_K\_S, stock | 12.97 tok/s | | Ridge tuned Q4\_K | 22.23 tok/s | | DAS Lab tuned Q4\_K | 22.36 tok/s | | DAS Lab IQ3\_S tuned MTP | 21.42 tok/s | - Benchmarks: all speeds come from the author's runs on one Arc Pro B60 with 24 GB, so treat them as a single data point. - Speculative decoding: the card reports 41.28 tok/s and 41.88 tok/s on the embedded-MTP variants, with no external drafter memory. - Prefill: about 245 tok/s on the Ridge tuned file. - License: apache-2.0. - Cost to run: no API key, account or paid service is named, but you need an Intel Arc GPU. - Data it reaches: you download files from Hugging Face, and the card names no other access. - Not for: other GPU brands, which the card does not cover. ## README ````markdown # Qwen3.8-27B Intel Arc Tuned Runs a 27B Qwen3.8 model in GGUF files retuned for Intel Arc GPUs, with pure decode near 22 tokens a second in the author's tests. For people running llama.cpp with SYCL on Arc cards. Made by Greatjedi on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: This repository holds GGUF weights of a 27B Qwen3.8 model, converted so they run fast on Intel Arc GPUs. The author says common 27B quantizations stall on Arc because the SYCL backend of llama.cpp lacks kernels for I-Quant tensors. The tuned files turn those tensors into Q4_K. Who it suits: It suits people with an Intel Arc GPU, such as the Arc Pro B60 or the A770, who run language models locally with llama.cpp. The card lists English and Chinese. ```table Title: Who runs it Industry | Who uses it | How they use it | Example Software | Developers with Intel Arc cards | Run a 27B model locally with llama.cpp SYCL | A local coding assistant on an Arc GPU Home labs | Local AI hobbyists | Get usable speed from an Arc card | Chat with a 27B model on an Arc Pro B60 Research | Quantization researchers | Study why I-Quants stall on SYCL | Compare the stock and tuned files ``` If you run an NVIDIA or Apple GPU, you can skip it. The card gives no figures for other hardware. Where to use it: - llama.cpp with the SYCL backend, on Intel Arc GPUs - Arc Pro B60 with 24 GB, Arc A770 with 16 GB and Battlemage cards, according to the card - The oneAPI SYCL runtime ```table Title: Jobs it does Use case | Who | What they get back Plain generation | Local users | Faster decode than the stock I-Quant files on Arc Speculative decoding | Speed seekers | Over 41 tokens a second with the embedded prediction head ``` How to set it up: - An Intel Arc GPU with enough memory for a file of about 14 to 15 GiB - llama.cpp built with the SYCL backend - Python, only to download the files with the Hugging Face tools 1. Install the Hugging Face Hub tools. 2. Download the repository files. 3. Load the tuned GGUF file in llama.cpp on the Arc GPU. ```sh pip install -U huggingface_hub hf download Greatjedi/Qwen3.8-27B-Intel-Arc-Tuned-GGUF ``` How to use it: Load a tuned file in llama.cpp with full GPU offload. The author measured speeds with 99 offloaded layers and flash attention on, on the Level Zero device. The newest file keeps an embedded prediction head, so speculative decoding needs no extra drafter model. ```sh hf download Greatjedi/Qwen3.8-27B-Intel-Arc-Tuned-GGUF ``` Example: You load the tuned Q4_K file on an Arc Pro B60 and ask the model a question. In the author's tests, pure decode ran at about 22 tokens a second against 8.10 for a stock IQ3_XXS file. Your own speed will depend on your setup. For newcomers and experts: If you are new, a quantized file is a shrunken copy of a model, and some shrinking styles run badly on some graphics cards. The first small thing to try is downloading one tuned file and loading it the way you load any GGUF. If you know the field, Intel's XMX engines use DPAS, which needs dense integer types. The author says I-Quant codebooks need table lookups and have no SYCL kernels, so they fall back to the host. The tuned files convert them to Q4_K with 6-bit scales and keep RoPE, layernorms and attention projections. The trade-off is size: files are 13.72 to 15.29 GiB. ```flow Find I-Quant tensors in the file Convert them to Q4_K blocks Keep sensitive tensors untouched Load the file in llama.cpp SYCL ``` Good to know: ```chart Title: Pure decode speed on an Intel Arc Pro B60 ISTA-DASLab IQ3_XXS, stock: 8.10 tok/s Ridge, stock: 12.22 tok/s Unsloth UD-Q4_K_S, stock: 12.97 tok/s Ridge tuned Q4_K: 22.23 tok/s DAS Lab tuned Q4_K: 22.36 tok/s DAS Lab IQ3_S tuned MTP: 21.42 tok/s ``` - Benchmarks: all speeds come from the author's runs on one Arc Pro B60 with 24 GB, so treat them as a single data point. - Speculative decoding: the card reports 41.28 tok/s and 41.88 tok/s on the embedded-MTP variants, with no external drafter memory. - Prefill: about 245 tok/s on the Ridge tuned file. - License: apache-2.0. - Cost to run: no API key, account or paid service is named, but you need an Intel Arc GPU. - Data it reaches: you download files from Hugging Face, and the card names no other access. - Not for: other GPU brands, which the card does not cover. ## On Hugging Face, 13 November 2026 - Task: text generation - Parameters: 26.9B - Weights: about 13.4 GB at 4-bit (estimate) - Formats: GGUF - Downloads in the last 30 days: 7,481 - Likes: 31 - License: apache-2.0 - Languages: en, zh - Based on: empero-ai/Qwen3.8-27B-Ridge-GGUF - Tags: gguf, intel-arc, intel-arc-b60, battlemage, sycl, qwen, qwen3.8, quantized, speculative-decoding, hardware-accelerated, iq3-s, text-generation ## Links - Model: https://huggingface.co/Greatjedi/Qwen3.8-27B-Intel-Arc-Tuned-GGUF - Files: https://huggingface.co/Greatjedi/Qwen3.8-27B-Intel-Arc-Tuned-GGUF/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download Greatjedi/Qwen3.8-27B-Intel-Arc-Tuned-GGUF ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [Greatjedi/Qwen3.8-27B-Intel-Arc-Tuned-GGUF on Hugging Face](https://huggingface.co/Greatjedi/Qwen3.8-27B-Intel-Arc-Tuned-GGUF) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | Qwen3.8-27B Intel Arc Tuned (this page) | 7,481 | 31 | 26.9B | apache-2.0 | 2026-10-09 | | [Qwen3.8-Flash-Coder APEX-I-MiniPlus V2.1 GGUF](https://mindket.com/p/238d4a60-b5ce-4e02-a828-5e9dce37a102) | 1,585 | 8 | 42.6B | apache-2.0 | 2026-10-11 | | [Qwen3.8-27B-NVFP4-DGX-SPARK](https://mindket.com/p/a7666325-428a-4e43-b11c-5fec915dc5df) | 41,306 | 1,127 | 18.2B | apache-2.0 | 2026-10-28 | | [Qwen3.8-27B-pi](https://mindket.com/p/8adc35eb-a424-4e6e-99cc-f4ae26715a1a) | 1,857 | 87 | 27.8B | apache-2.0 | 2026-09-30 | | [Qwen3.8-27B-DSpine-b16-GGUF](https://mindket.com/p/9955f2b3-7961-45ce-b63c-5a324a506318) | 15,022 | 41 | 2B | apache-2.0 | 2026-11-09 | | [Mellum2.1-12B-A2.5B-Thinking-GGUF](https://mindket.com/p/6b181e24-213d-4fc2-a178-72da0b212f88) | 422,635 | 172 | 12.1B | apache-2.0 | 2026-10-22 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-10-09 - First published: 2026-09-17 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open Greatjedi/Qwen3.8-27B-Intel-Arc-Tuned-GGUF on Hugging Face](https://huggingface.co/Greatjedi/Qwen3.8-27B-Intel-Arc-Tuned-GGUF) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/83aecdc8-7c11-4fdd-a57d-ac9e89b7742c) - [Its page on Mindket](https://mindket.com/p/83aecdc8-7c11-4fdd-a57d-ac9e89b7742c)