---

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, agent]

language: [en]

pipeline_tag: text-generation

---

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

> Q8_0_ROCMFPX_AGENT is a ROCmFPX quant type — it exists only in

> charlie12345/ROCmFPX, not upstream llama.cpp.

>

> 📦 26.28 GiB, 8.39 bpw · ✅ tools 7/7 both modes

> 🚀 26.62 tok/s with MTP — 6.2% faster than the plain 8-bit build, because it accepts

> more draft tokens (0.953 vs 0.911). ⚠️ Without MTP the two are indistinguishable.

Qwen3.8-27B — ROCmFPX 8-bit AGENT routing (Q8_0_ROCMFPX_AGENT) GGUF

The agent / tool-call coherent 8-bit ROCmFPX routing of Qwen3.8-27B for **AMD gfx1151

(Ryzen AI MAX+ 395 / Strix Halo). Quantized from the 51.3 GiB BF16** GGUF.

| | |

|---|---|

| File | Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf |

| Size | 26.2767 GiB (28,214,425,952 bytes) |

| BPW | 8.39 |

| ftype | Q8_0_ROCMFPX_AGENT (115) |

| sha256 | f3ef2bdbf56e244fff14b72114dc2aa300b84a4cb4eaf54f2e5e4da1cfcae10b |

---

⚖️ Why this variant exists — and when it does NOT

The routing difference is structural. Across the 17-tensor *output.weight group:

| build | Q8_0 | ROCmFPX 8-bit (TYPE_103) |

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

| plain Q8_0_ROCMFPX | 1 | 16 |

| this (_AGENT) | 13 | 4 |

AGENT keeps 12 more attention-output projections at full Q8_0 — that is what the extra

0.35 GiB buys.

With MTP, that buys real speed

Ryzen AI MAX+ 395 (gfx1151, ROCm 7.2.4), median of 3, warm-up discarded, idle box, shipped

flags (--spec-type draft-mtp, Q4_0 draft head, --spec-draft-n-max 4):

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

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

| plain Q8_0_ROCMFPX | 25.92 GiB | 25.07 tok/s | [25.07 – 25.51] | 0.911 |

| this _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 |

+6.2% over plain, ranges disjoint. The mechanism is visible in the acceptance rate: keeping

more attention-output precision makes the MTP draft head's guesses land more often, so more

speculated tokens survive verification.

⚠️ Without MTP there is no measurable difference

Run standalone, the two builds are 7.92 vs 7.82 tok/s (this one marginally slower), and both

score 7/7 tool calling in thinking and non-thinking — identical across multi-arg,

nested-object, enum, declines, multi-turn, streaming and parallel calls. Our 7-case suite cannot

separate them.

⇒ Take this variant if you serve with MTP. Take the plain build if you do not.

And if you want raw throughput, the 4-bit build beats both by ~1.44×.

llama-server -m Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.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

17×23 ⇒ ✅ 391 · capital of Japan ⇒ ✅ Tokyo · days in 2024 ⇒ ✅ 366 ·

tools 7/7 thinking, 7/7 non-thinking.

token_embd.weight Q8_0, 851 tensors, arch=qwen35.

🩹 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, no quality A/B vs BF16 or the plain 8-bit build. We have shown a structural

difference in tensor types and no measurable behavioural difference.

• No long-context testing (131,072 supported), no coding/reasoning benchmark.
• Our tool suite is 7 cases. A 7/7 tie is not proof of equivalence — it is the limit of what

this instrument can resolve. The MTP acceptance rate did separate the builds where the tool

suite could not.

• An earlier revision of this card said no advantage over the plain build could be measured. That

was true without MTP and wrong with it; the table above supersedes it.

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