Skip to page content
SAVRN
Search Plan a project

Organization

Hipfire

hipfire-models

Rust-based, fast inference engine optimized for AMD

Models in Library2
Datasets in Library0
Models on Hugging Face37
Followers27

Compare the published evidence

This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.

Reported licenses: apache-2.0, other. Open a record to review its specific license and conditions.

Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.

Models

Text-only Qwen3.8-27B artifacts for hipfire, the Rust-native LLM inference engine for AMD GPUs. This repository contains the admitted MQ3V2 through MQ6V2 product ladder, the MQ4L (MQ4V2-Lloyd) tiers, and matching DFlash drafters. MQ4V2 supersedes MQ4V1 as hipfire's canonical mq4 product. Artifacts remain self-describing by HFQM quant-type ID; old MQ4V1 files are still readable but are not the current product. Each bit-width has exactly three tiers: - mqN-xt: embeddings protected; lmhead and recurrent outputs remain at the base codec. - mqN: embeddings and lmhead protected. - mqN-pro: recurrent/SSM outputs also lifted. MQ3 Pro uses ssmout:mq6v2 to stay inside the 3.x model-bpw class. mq4-xt…

Open weights apache-2.0 hipfire
View model

is published. The canonical filename is qwen3.8-flash-next.mq4-xts (MQ4 XTS). The older qwen3.8-flash-next-gptq3.mq4 filename is a legacy alias for the same bytes, retained through hipfire 0.4.x and at least 90 days. qwen3.8-flash-next.mq4-xts holds a requant of the routed experts. The other 1227 tensors are byte-identical to the previous file, which keeps its name qwen3.8-flash-next.mq4: the hipfire v0.4.0 registry pins that name to sha256 8aa01cf4…, so changing its bytes would fail those users' pulls. Wherever this card says qwen3.8-flash-next.mq4 below, it means those RTN-asymmetric bytes. 262,144-token calibration corpus disjoint from WikiText-2 (calibration.u32, sha256…

Open weights other hipfire
View model