This repository contains optimized **ROCmFP4** and **ROCmFP8** GGUF releases of **Qwen 3.8 27B**, custom-engineered for **AMD Strix Halo (Ryzen AI Max+ 395 / Radeon 8060S)** and **AMD Radeon discrete GPUs**. > 🛠️ **Unified HaloFPX Server:** github.com/julianmb/halofpx (Multi-model zoo, hot-swapping, OpenAI API) > 📖 **Qwen 3.8 Dedicated Deep-Dive:** github.com/julianmb/q38rocm (Standalone optimization report, benchmarks & tuning) Strix Halo features a **50 TOPS XDNA 2 NPU** (`/dev/accel/accel0`). Extensive empirical benchmarking demonstrates: - **Sustained Decode Ceiling:** **33.8 tok/s** via embedded MTP (iGPU only) is the practical ceiling. The NPU does *not* improve sustained decode speed. - **Proven NPU Value:** **1.8× faster first-token TTFT on long prompts (870 ms vs 1587 ms)** via hybrid NPU-burst → iGPU handoff (`scripts/run_pipeline.py`). - **See `docs/NPU_INTEGRATION.md`** for complete setup instructions.

Text generation

Input Text→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

Qwen3.8-Flash-Next-IQ4_XS-GGUF

julianmb

second-generation quant: same trunk type (iq4_xs), but calibrated with a 926-entry imatrix (1,024 chunks) via the ROCmFPX banded quantizer, and the 51B PLE lookup table **left at q8_0** (no `--tensor-type` cut). 5.56 bpw, 115 giB — 24 giB bigger than the 91g PLE file. pick M2 when you want the **best measured quality** and don't mind the 24 giB: at ≤32k plain it matches PLE, and at 32k MTP it measured fastest. for shallow-depth MTP speed take the 91g PLE; for deep 128k+ MTP the static 116g had a small in-sweep edge (17.4 vs 13.3/13.5 — within the same-config spread, n=1 caveat). every quant descends from an F16 that was byte-verified against the official `Qwen/Qwen3.8-Flash-Next-FP8` checkpoint: hyper-connection norms folded to (1 + w) (97/97 tensors — the converter bug that produces deterministic garbage is fixed in our pipeline), PLE fp8 scale applied, expert stacking identity probed 512x3, GDN v-head reorder checked. details: https://github.com/julianmb/haloq38flash

Text generation

Input Text→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

COST EXPLORER

Great models. Clear costs.

Cost analysis

Adjust monthly token usage to compare estimated API costs.

Monthly input tokens 10 MMonthly output tokens 2 M1 M = 1 million tokens · USD
Compares base text-token rates within the same channel

Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.

MODEL HANDBOOK

Understand before you choose

Selection guide & FAQ

How should API prices be compared?+

Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.

Do open weights mean free commercial use?+

Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.

Is the top-ranked model the best for me?+

Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.

Find your ideal AI model.

Explore AI models 5

MiniCPM5-2B-NPU2

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUF

Ornith-1.5-35B-A3B-ROCmFP4-GGUF

Qwen-3.8-27B-ROCmFP4-FAST-GGUF

Qwen3.8-Flash-Next-IQ4_XS-GGUF

No matching models

Great models. Clear costs.

Understand before you choose

Follow trends. Find tools. Explore models.