---

license: apache-2.0

base_model: Qwen/Qwen3.8-27B

base_model_relation: quantized

tags: [gguf, llama.cpp, rocm, gfx1151, strix-halo, amd, ryzen-ai-max-395, ai-max-395, rocmfpx, moe, tool-calling]

language: [en]

pipeline_tag: text-generation

---

> ### ⚠️ STOCK llama.cpp WILL NOT LOAD THIS MODEL

> Q8_0_ROCMFPX is a ROCmFPX quant type — it exists only in

> charlie12345/ROCmFPX, not upstream llama.cpp.

> Ignore the auto-generated "Use this model" commands above.

>

> 📦 25.92 GiB, 8.28 bpw · ✅ tools 7/7 in BOTH thinking and non-thinking

> 🚀 25.07 tok/s with MTP on Ryzen AI MAX+ 395. ⚠️ The 4-bit build is still faster (38.32).

> ⚠️ Run it WITH the bundled MTP draft head — without it you get ~7.9 tok/s, a third of the speed.

Qwen3.8-27B — ROCmFPX 8-bit (Q8_0_ROCMFPX) GGUF

An 8-bit ROCmFPX quantization of Qwen3.8-27B for **AMD gfx1151 (Ryzen AI MAX+ 395 /

Strix Halo)**, built because 128 GB of unified memory makes 8-bit genuinely affordable on this

hardware. Quantized from the 51.3 GiB BF16 GGUF — not requantized from a lower-bit build.

| | |

|---|---|

| File | Qwen3.8-27B-Q8_0_ROCMFPX.gguf |

| Size | 25.9232 GiB (27,834,808,672 bytes) |

| BPW | 8.28 |

| ftype | Q8_0_ROCMFPX (111) |

| sha256 | 960978d5b230485c35c2456988082fa5d1e27a05ac74150604127b0e95b904bf |

---

Benchmarks — run this WITH the MTP draft head

Ryzen AI MAX+ 395 (gfx1151, 128 GB unified, ROCm 7.2.4), **median of 3, warm-up discarded,

idle box**, shipped serving flags: `--spec-type draft-mtp --model-draft mtp-Qwen3.8-27B-Q4_0.gguf

--spec-draft-n-max 4 -ngl 999 -fa on -fit off`.

| build | size | decode WITH MTP | range | draft acceptance |

|---|---|---|---|---|

| this (Q8_0_ROCMFPX) | 25.92 GiB | 25.07 tok/s | [25.07 – 25.51] | 0.911 |

| Q8_0_ROCMFPX_AGENT | 26.28 GiB | 26.62 tok/s | [26.61 – 27.15] | 0.953 |

| Q4_0_ROCMFP4_STRIX (4-bit) | 14 GiB | 38.32 tok/s | [37.91 – 38.61] | 1.000 |

⚠️ Without the draft head this model runs at ~7.9 tok/s — MTP is worth 3.2× here. The

draft head (mtp-Qwen3.8-27B-Q4_0.gguf) is included in this repo; use it.

Choosing: the 4-bit build is ~1.53× faster and 12 GiB smaller. Take 8-bit for fidelity

headroom, not throughput. And if you are running MTP, prefer the AGENT variant — it accepts

more draft tokens (0.953 vs 0.911) and is 6.2% faster despite being marginally larger.

llama-server -m Qwen3.8-27B-Q8_0_ROCMFPX.gguf \
  --spec-type draft-mtp --model-draft mtp-Qwen3.8-27B-Q4_0.gguf \
  --spec-draft-ngl 99 --spec-draft-n-max 4 \
  -ngl 999 -fa on -fit off --jinja --ctx-size 32768

Verified

| check | result |

|---|---|

| 17 × 23 | ✅ 391 |

| capital of Japan | ✅ Tokyo |

| days in 2024 | ✅ 366 |

| tool calling — thinking | ✅ 7/7 (multi-arg, nested-object, enum, declines, multi-turn, streaming, parallel) |

| tool calling — non-thinking | ✅ 7/7 |

Per-tensor types (audited, 851 tensors)

output.weight Q8_0 · token_embd.weight Q8_0 · bulk TYPE_103 (ROCmFPX 8-bit layout).

🩹 Prompt caching with the MTP draft head — fixed

Reported by a user of this repo: with --spec-type draft-mtp loaded, llama-server disabled

prefix caching entirely. Every agentic turn reprocessed the whole prompt. Reproduced here on an

8045-token stable prefix:

| config | prompt_n | cache_n | prompt_ms |

|---|---|---|---|

| no draft head | 519 | 7526 reused | 1 908 |

| draft head (the defect) | 8045 | 0 | 27 948 |

| draft head + this patch | 4 | 5101 | 100 |

279× less prompt processing per turn, with MTP still drafting.

Root cause

The saved speculative state is the MTP boundary — the target model's pre-norm hidden row at the

cached prompt's exact end position. Any partial-prefix reuse would leave it describing a position

that no longer exists, so the server demanded an exact full-prefix match and otherwise reprocessed

cold, erasing its own context checkpoints on the way.

The fix

patches/mtp-prompt-cache-fix.patch (4 files, applies to 2809dc5) captures the speculative

boundary inside the context checkpoint (common_prompt_checkpoint::data_spec).

create_checkpoint runs between decode batches — exactly where that boundary is valid — so exact

state is saved and restored together with the KV, never rebuilt.

⛔ Two approaches were tried first and rejected: rebuilding the boundary from a zero-fill

changed the model's output (deterministically, 3/3), and truncating the KV back to the reuse point

is impossible here — the bounded rollback window is 4 tokens against the 333 a real turn needs.

Exact state restore is the only shape that preserves output.

Verification

Independently gated 10/10: same prompt cold vs warm, temperature 0, byte-identical every run,

with the cache genuinely engaged (cache_n=5101, not a vacuous pass). The output hash also matches

the unpatched build, so behaviour is unchanged. Fails closed — an unreachable rollback logs

reason=spec-checkpoint-missing and cold-reprocesses rather than guessing.

Related upstream

This is the same family as open llama.cpp issues

#20225,

#19794 and

#24055 — checkpoints being invalidated on

hybrid/recurrent models. This patch is not upstreamed; it is offered here as-is.

What was NOT measured

• No perplexity run, and no quality A/B vs BF16 or the 4-bit build. We show 8-bit is

slower; we have not demonstrated it is better. If you need proof that 8 bits buys

accuracy here, that measurement does not yet exist.

• An earlier revision of this card quoted 7.92 vs 13.84 tok/s. Those were measured **without the

MTP draft head** and understated both builds; the table above supersedes them.

• No long-context testing (model supports 131,072).
• No coding/reasoning benchmark.

Base model licence inherited. Credit for the model goes to Qwen.