Qwen3.6-27B-ROCmFPX

philtheriver/Qwen3.6-27B-ROCmFPX

Qwen3.6-27B-ROCmFPX is a text generation model from philtheriver. Use it when you need the model to write or continue text. It is set up for llama.cpp. The card lists the license as apache-2.0.

ROCmFPX 3→8-bit quants of unsloth/Qwen3.6-27B-MTP-GGUF — the general-purpose base, with MTP speculative decoding + Qwen3-VL vision. Neutral imatrix calibration, so base behavior is preserved (not skewed toward code).

Downloads · 30 days

116

7% of all-time downloads

All-time downloads

1.6K

Public

Repo size

91.9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf91.9 GB · 100%

At a glance

Task: Text Generation
Library: llama.cpp
License: apache-2.0
Access: Public
Created: Jun 22, 2026
Updated: Jun 23, 2026
SHA: 61ed44a5

Try a prompt

Base models

unsloth/Qwen3.6-27B-MTP-GGUF

Model card

From the Hugging Face model README

Qwen3.6-27B · ROCmFPX

Stock `Q6_K` quality, ~30% faster prompt-processing on AMD Strix Halo (`gfx1151`)

ROCmFPX 3→8-bit quants of unsloth/Qwen3.6-27B-MTP-GGUF — the general-purpose base, with MTP speculative decoding + Qwen3-VL vision. Neutral imatrix calibration, so base behavior is preserved (not skewed toward code).


Quality	≈ stock `Q6_K` (PPL within error)
Prompt processing	+29% vs Q6_K (short ctx) → +20% at 64k — measured
Decode	~18 tok/s with MTP (~9 raw)
Vision	Qwen3-VL — bundled `mmproj/`

⚠️ Requires the ROCmFPX fork (build main — the FP* types are merged in) — custom AMD quant types (enum IDs 110–115), not upstream-stable. Won't load in stock llama.cpp / LM Studio / Ollama. HF's precision badge is wrong — pick the file by name.

Pick a tier

File suffix	Size	Best for
`…embF16-headQ6-Q6_0_ROCMFPX.gguf` ★	23G	best overall — the flagship
`…embF16-Q8_0_ROCMFPX.gguf`	28G	maximum fidelity
`…embF16-Q4_0_ROCMFP4.gguf`	19G	fastest decode (4-bit)
`…embF16-Q3_0_ROCMFPX.gguf`	16G	smallest

All filenames prefixed Qwen3.6-27B-STRIX-.

Quick start

# build the fork once — main already has the ROCmFPX quant types
git clone https://github.com/charlie12345/ROCmFPX.git && cd ROCmFPX
JOBS=16 scripts/build-strix-rocmfp4-mtp.sh

# serve the flagship — MTP + vision
HSA_OVERRIDE_GFX_VERSION=11.5.1 build-strix-rocmfp4/bin/llama-server \
  -m Qwen3.6-27B-STRIX-embF16-headQ6-Q6_0_ROCMFPX.gguf \
  -dev ROCm0 -ngl 999 -fa on -c 32768 \
  --spec-type draft-mtp --spec-draft-ngl all --spec-draft-n-max 2 \
  --jinja --mmproj mmproj/mmproj-F32.gguf --host 0.0.0.0 --port 8080

Tool calls: serve with --jinja so the model's own chat template emits them — no special parser flag needed.

<details> <summary><b>All tiers · recipe · benchmarks</b></summary>

All tiers

File suffix	Preset	Enum	Size	Role
`embF16-headQ6-Q6_0_ROCMFPX.gguf`	`Q6_0_ROCMFPX`	110	23G	flagship — f16 emb + Q6_K head + imatrix
`embF16-Q8_0_ROCMFPX.gguf`	`Q8_0_ROCMFPX`	111	28G	highest fidelity
`embF16-Q4_0_ROCMFP4.gguf`	`Q4_0_ROCMFP4`	100	19G	fastest decode (4-bit body)
`embF16-Q3_0_ROCMFPX.gguf`	`Q3_0_ROCMFPX`	112	16G	smallest

f16 token embeddings throughout. (HF labels Q4/Q8 but not Q6/Q3 — the latter aren't standard llama.cpp quant names; pick by filename.)

Verification (Strix Halo gfx1151)

Metric	Value
Functional smoke	chat/coding/JSON/tool-call/coherency ✅ (5/5)
PPL vs `Q6_K`	flagship 5.7030 vs stock `Q6_K` 5.6618 → Δ +0.73% (general slice, ctx 512)

Performance — prompt-processing throughput (t/s) vs `Q6_K`

Context	`Q6_K`	flagship	Δ
pp512	188	242	+29%
pp2048	191	245	+28%
pp10k	180	228	+27%
pp16k	172	217	+26%
pp32k	156	193	+23%
pp64k	133	159	+20%

Clean dedicated-GPU llama-bench (both servers stopped, warm-up pass discarded). The gfx1151-tuned ROCmFPX kernels win the compute-bound prefill — the edge is largest at short context and narrows to +20% at 64k as O(n²) attention takes over. Decode is bandwidth-bound (≈ Q6_K raw), and MTP (--spec-type draft-mtp) ~doubles it in serving. Single-rep llama-bench; treat absolutes as ±a few %.

</details>

Credits & license

Apache-2.0 (inherited). Qwen3.6 (base) → charlie12345 / ROCmFPX (quant fork). ROCmFPX quantization by this repo's author.

Task: Text Generation
Library: llama.cpp
License: apache-2.0
Languages: en
Created: Jun 22, 2026
Updated: Jun 23, 2026