---
license: apache-2.0
base_model: Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF
base_model_relation: quantized
pipeline_tag: text-generation
library_name: llama.cpp
language:
- en
tags:
- gguf
- rocmfpx
- rocm
- amd
- strix-halo
- gfx1151
- mtp
- speculative-decoding
- agent
- tool-use
- code
- qwen3
- vision
---

# Qwopus3.6-27B-Coder · ROCmFPX

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

ROCmFPX 3→8-bit quants of [`Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF`](https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF) — 27B, MTP speculative decoding + Qwen3-VL vision, agent/tool-use tuned.

| | |
|---|---|
| **Quality** | ≈ stock `Q6_K` — PPL **+0.17%** (within error) |
| **Prompt processing** | **+32%** vs Q6_K (short ctx) → +22% at 64k |
| **Decode** | \~18 tok/s with MTP (~9 raw) |
| **Vision** | Qwen3-VL — bundled `mmproj/` |

> ⚠️ **Requires the [ROCmFPX fork](https://github.com/charlie12345/ROCmFPX)** (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_AGENT.gguf` ★ | 26 GB | **best overall** — the flagship |
| `…embF16-Q8_0_ROCMFPX.gguf` | 29 GB | maximum fidelity |
| `…embF16-Q4_0_ROCMFP4.gguf` | 19 GB | fastest decode (4-bit) |
| `…embF16-Q3_0_ROCMFPX.gguf` | 17 GB | smallest |

Agent-routed `_AGENT` tiers + the full enum/bpw table are in the details below and the **Files** tab. All filenames prefixed `Qwopus3.6-27B-Coder-MTP-STRIX-`.

## Quick start

```bash
# 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 Qwopus3.6-27B-Coder-MTP-STRIX-embF16-headQ6-Q6_0_ROCMFPX_AGENT.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: point your client at the **`qwen3_coder`** parser, or the model narrates code instead of emitting structured calls.

**Better tool-calling / agent compatibility (optional).** These ROCmFPX quants carry the exact weights of [`Jackrong/Qwopus3.6-27B-Coder`](https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder), so the interoperability-hardened chat template from Jackrong's [**Compat-MTP edition**](https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF) (JSON-string + mapping/list tool args; llama.cpp/minja ↔ HF-Jinja parity) drops in unchanged. If your agent runtime hits flaky function-calling, grab [`chat_template_compat.jinja`](chat_template_compat.jinja) from this repo and serve with `--chat-template-file chat_template_compat.jinja` (overrides the bundled `--jinja` template). Same weights, just a more portable template.

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

### All tiers

| File suffix | Preset | Enum | Size | Role |
|---|---|---|---|---|
| `embF16-headQ6-Q6_0_ROCMFPX_AGENT.gguf` | `Q6_0_ROCMFPX_AGENT` | 114 | 26 GB | flagship — f16 emb + Q6_K head + imatrix |
| `embF16-Q8_0_ROCMFPX_AGENT.gguf` | `Q8_0_ROCMFPX_AGENT` | 115 | 30 GB | highest-fidelity agent |
| `embF16-Q8_0_ROCMFPX.gguf` | `Q8_0_ROCMFPX` | 111 | 29 GB | highest fidelity |
| `embF16-Q6_0_ROCMFPX.gguf` | `Q6_0_ROCMFPX` | 110 | 24 GB | balanced |
| `embF16-Q3_0_ROCMFPX_AGENT.gguf` | `Q3_0_ROCMFPX_AGENT` | 113 | 21 GB | smallest agent |
| `embF16-Q3_0_ROCMFPX.gguf` | `Q3_0_ROCMFPX` | 112 | 17 GB | smallest |
| `embF16-Q4_0_ROCMFP4.gguf` | `Q4_0_ROCMFP4` | 100 | 19 GB | fastest decode (4-bit body) |

f16 token embeddings throughout; `_AGENT` presets keep attention/FFN routing at higher precision for tool-call/JSON coherence. (HF labels `Q4`/`Q8` but not `Q6`/`Q3` — the latter aren't standard llama.cpp quant names.)

### Verification (Strix Halo gfx1151)

| Metric | Value |
|---|---|
| Functional smoke | chat/coding/JSON/tool-call/coherency ✅ (5/5) |
| PPL vs `Q6_K` (code corpus) | flagship **2.922** vs Q6_K **2.917** → **+0.17%** (within ±0.04) |

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

| Context | `Q6_K` | flagship | Δ |
|---|---|---|---|
| pp512 | 204 | 269 | **+32%** |
| pp2048 | 193 | 254 | +31% |
| pp10k | 181 | 236 | +30% |
| pp16k | 174 | 225 | +29% |
| pp32k | 158 | 199 | +26% |
| pp64k | 134 | 163 | **+22%** |

The gfx1151-tuned kernels win the compute-bound prefill; the edge is largest at short context and narrows toward +22% 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. `Q4_0_ROCMFP4` is the decode king (~13 tok/s raw). *Single-rep `llama-bench`; treat absolutes as ±a few %.*

</details>

## Credits & license

Apache-2.0 (inherited). Jackrong + Kyle Hessling (fine-tune) → Qwen3.6-27B (base) → [charlie12345 / ROCmFPX](https://github.com/charlie12345/ROCmFPX) (quant fork). ROCmFPX quantization by this repo's author.