---

license: apache-2.0

base_model:

- ornith-ai/Ornith-1.5-35B-A3B

base_model_relation: quantized

library_name: llama.cpp

pipeline_tag: text-generation

tags:

- gguf

- rocm

- rocmfpx

- rocmfp4

- rocmfp6

- amd

- strix-halo

- gfx1151

- mtp

- speculative-decoding

- moe

---

Ornith-1.5-35B-A3B — ROCmFPX builds for Strix Halo

ROCmFPX quantisations of Ornith-1.5-35B-A3B

for AMD Strix Halo (gfx1151), with the MTP head kept live for speculative decoding.

| file | bpw | size | pick it for |

| --- | ---: | ---: | --- |

| Ornith-1.5-35B-HYBRID-fp6.gguf | 4.41 | 18.21 GiB | prefill-dominated work — best quality |

| Ornith-1.5-35B-ROCMFP4-FAST.gguf | 4.27 | 17.65 GiB | generation-dominated work — fastest decode |

More variants may be added later.

HYBRID: class-aware assignment

Every stock ROCmFP4 preset leaves the obvious lever unused on a 256-expert MoE: they apply **one

type to every tensor**. The hybrid splits them:

| tensor class | count | type |

| --- | ---: | --- |

| routed experts | 123 | Q4_0_ROCMFP4_FAST (4.25 bpw) |

| attention | 104 | Q6_0_ROCMFPX (FP6) |

| shared expert | 123 | Q6_0_ROCMFPX (FP6) |

| token embedding / output | 2 | Q6_0_ROCMFPX (FP6) |

| MTP (nextn) head | 1 | Q4_0_ROCMFP4_FAST |

4.41 bpw · 18.21 GiB. Routed experts are sparse (8 of 256 fire per token) and tolerate 4-bit;

attention and the shared expert are on every token's critical path and get 6-bit.

Perplexity

wikitext-2, 145 chunks @ ctx 2048, identical corpus, Vulkan, all measured here:

| build | bpw | size | PPL |

| --- | ---: | ---: | --- |

| HYBRID (this) | 4.41 | 18.21 GiB | 7.3991 ±0.0506 |

| ROCMFP4_FAST | 4.27 | 17.65 GiB | 7.7749 ±0.0539 |

| ROCMFP4_COHERENT | 4.55 | 18.81 GiB | 7.8233 ±0.0550 |

| ROCMFP4_STRIX | 4.31 | 17.81 GiB | 7.8307 ±0.0547 |

The three stock presets cluster within 0.8% of each other — preset choice barely matters on this

architecture, because none of them differentiate by tensor class. Class-aware assignment moves

4.8% for +0.14 bpw.

Perplexity measures prose next-token prediction, not agentic capability. Use it to compare

quantisations of the same weights, not to rank models.

Speed (Radeon 8060S, gfx1151, Vulkan, MTP n4, -ub 2048)

| build | 8.5K pp / tg | 34K pp / tg | 69K pp / tg |

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

| HYBRID | 990.9 / 63.0 | 815.9 / 55.6 | 488.4 / 45.2 |

| FAST | 993.9 / 87.7 | 813.3 / 67.3 | 478.9 / 56.3 |

Prefill is identical (within 0.5%) — it is compute-bound, so the FP6 weights cost nothing there.

Decode pays the whole price: −28%, because FP6 attention means more bytes per generated token.

⇒ Pick HYBRID for prefill-dominated work (digesting repos/documents, long context, short

answers). Pick FAST for generation-dominated work. The recipe is a quality/decode dial, not a

free win.

Needle-in-a-haystack retrieval passes at 8.5K, 34.5K and 69.5K on both.

Backend: use Vulkan

Same build, same model, same flags — only -dev changes:

| backend | 8.5K pp / tg | 34K pp / tg |

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

| Vulkan | 993.9 / 87.7 | 813.3 / 67.3 |

| HIP · ROCm 7.2.4 | 968.1 / 72.7 | 675.3 / 64.1 |

| HIP · ROCm 10.1 nightly | 1087.0 / 58.2 | 834.6 / 55.1 |

The ROCm nightly is a prefill-for-decode trade: +12% prefill over HIP 7.2 but −20% decode, and

−34% decode against Vulkan. Vulkan wins overall and needs no container.

MTP head at FP4 is safe here

The nextn.eh_proj head is often kept at Q8_0 on the theory that it determines draft acceptance.

Measured on this model, dropping it to FP4 did not hurt — identical perplexity to 4 decimals

(7.7749 both) and slightly better acceptance:

| MTP head | acceptance |

| --- | --- |

| Q8_0 | 0.73–0.77 |

| FP4 | 0.78–0.80 |

Usage

llama-server -m Ornith-1.5-35B-HYBRID-fp6.gguf \
  -ngl 99 -c 131072 -dev Vulkan0 --jinja -fa on -b 2048 -ub 2048 \
  --spec-type draft-mtp --spec-draft-n-max 4 --spec-draft-p-min 0.6

Requires a ROCmFPX build — mainline llama.cpp does not

know the Q4_0_ROCMFP4_* / Q6_0_ROCMFPX tensor types. The MTP head is native to Ornith 1.5

(blk.40.nextn.*, nextn_predict_layers=1); no graft is needed, unlike 1.0.

Reproduce the recipe with:

attn_.*=q6_0_rocmfpx
ffn_(gate|up|down)_shexp=q6_0_rocmfpx
token_embd.weight=q6_0_rocmfpx
output.weight=q6_0_rocmfpx
nextn.*=q4_0_rocmfp4_fast

llama-quantize --tensor-type-file <rules> Ornith-1.5-35B-BF16.gguf out.gguf Q4_0_ROCMFP4_FAST

Honest caveat

On wikitext perplexity, Ornith 1.0 scores far better — 6.19 (ROCmFP4-COHERENT) against 7.40

here, and the gap is present at BF16, so it is a property of the 1.5 weights and not of this

quantisation. 1.0 also decodes faster (86.7 t/s) with higher draft acceptance (0.88).

Ornith 1.5 is chosen here for its reported agentic/SWE gains, which wikitext does not measure. If

your workload is prose modelling rather than agentic coding, 1.0 may serve you better.