Ling-3.0-tiny-ROCmFPX-Q8_0-GGUF

⚠️ STOCK llama.cpp WILL NOT LOAD THIS MODEL

7.62 GiB · 89.51 tok/s on a Ryzen AI MAX+ 395.

Ling-3.0-tiny — ROCmFPX 8-bit GGUF

An 8-bit ROCmFPX quantization for AMD gfx1151 (Ryzen AI MAX+ 395 / Strix Halo), quantized from BF16 GGUF — a lossless source, not a requantization of a lower-bit build.

Requires the Q-LoRA bailingmoe3 arch port (q_lora_rank=256). Our port is in patches/; without it no GGUF of this model loads at all.

⛔ Requires a llama.cpp with the ROCmFPX quant types

Q8_0_ROCMFPX (ftype 111) and Q8_0_ROCMFPX_AGENT (ftype 115) exist only in charlie12345/ROCmFPX, not upstream llama.cpp. Stock llama.cpp reports invalid ggml type 103. Ignore the auto-generated "Use this model" commands above.

---

All quant variants

Three builds of this model, all measured in one session on one box with one binary (Ryzen AI MAX+ 395, gfx1151, ROCm 7.2.4, ROCmFPX-2809dc5) — so these rows are directly comparable. Median of 3, warm-up discarded, otherwise-idle box.

⚠️ The 4-bit build is faster (104.04 vs ~89 tok/s) and 44% smaller. These 8-bit builds exist for accuracy headroom, not speed — pick them only if you need the extra precision.

What AGENT actually changes: it keeps far more tensors at true Q8_0 instead of the packed 8-bit type — measured in these files, 135 tensors vs 2 tensors. On models with an MTP draft head that raises draft acceptance and wins ~6%; these two models have no MTP head, and here the two 8-bit builds are within noise of each other.

Correctness: 3/3 clean on all three builds (391 · Tokyo · 366).

Per-tensor types (audited in this finished file)

output.weight Q8_0 · token_embd Q8_0 · 309 packed TYPE_103 · 215 F32 · 2 Q8_0

---

What was NOT measured

• No perplexity run, and no quality A/B against the source. The checks above are memorized-fact prompts — necessary but not sufficient; a damaged model can pass them.
• No long-context testing. · No tool-calling evaluation.

Base model licence inherited; credit for the model goes to its authors.