RX 9070

reported speed:

60.0 tokens/s generation

quant:

IQ3_XXS (GGUF)

kv:

K 8_0 / V 4_0

Reported by the source; GPU count, offloading and concurrent requests can change this figure. Check the full setup before comparing.

User reports Qwen3.8 27B at about 60 t/s on a 16 GB RX 9070 XT at 128k context. Setup uses the ISTA-DASLab GSQ-RCO IQ3_XXS GGUF with a HermiHg DFlash2 Q2_K_S draft model for speculative decoding, and a K 8_0 / V 4_0 KV cache. User says this beats the built-in MTP, which multiplies VRAM use, and calls it one of the best single-thread choices on a 16 GB GPU. Speculative decoding is more sensitive to GTT overflow, so disabling it is faster when exceeding VRAM on a DDR5 PCIe 5 system.

reported speed:

73.0 tokens/s generation

quant:

Q1_0

kv:

kvarn4

Reported by the source; GPU count, offloading and concurrent requests can change this figure. Check the full setup before comparing.

User reports 43.4 t/s with a q8_0 KV cache and 73.0 t/s with a kvarn4 KV cache at 120K context. The q8_0 cache used about 13.1 GB total and the kvarn4 cache about 9.8 GB total. The kvarn4 cache is 68% faster and uses 3.3 GB less VRAM.

reported speed:

40.7 tokens/s generation · 778.9 tokens/s prompt processing

quant:

IQ3_XXS (gguf)

kv:

Q8

Reported by the source; GPU count, offloading and concurrent requests can change this figure. Check the full setup before comparing.

User reports Qwen3.8-27B-UD-IQ3_XXS.gguf at 40.68 t/s generation and 778.91 t/s prompt processing at 131,072 context, against 13.36 t/s and 137.87 t/s at 65,536 context. Setup is llama-server with flash-attn, a q8_0 KV cache, Vulkan0, and speculative decoding with draft-mtp and ngram-mod. User asks why the smaller context degrades performance.

reported speed:

46.9 tokens/s generation · 398.4 tokens/s prompt processing

quant:

UD-Q5_K_XL (gguf)

flash attention:

on

mtp (multi-token prediction):

on

Reported by the source; GPU count, offloading and concurrent requests can change this figure. Check the full setup before comparing.

User reports generation around 45-52 t/s on two RX 9070 XTs with ROCm. Setup is MTP with spec-type = draft-mtp and spec-draft-n-max = 2, using the unsloth UD-Q5_K_XL GGUF. Prompt t/s varies, and draft acceptance rate is around 0.8-0.99. User praises the speed, smarts and steerability for agentic coding tasks.