llamaperf

AMD RX 9060 XT 16GB reports

11 reports. These are individual setups, not a controlled benchmark. AMD RX 9060 XT 16GB speeds and models →

Speeds are as each source reported them. GPU count, offloading and concurrent requests change them, and prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing two reports.

Qwen3.8 27B

2× AMD RX 9060 XT 16GB · llama.cpp · 32,768 ctx

AMD hardware
generation:
15-18 tokens/s
quant:
Q4 (GGUF)

User reports running Qwen3.8 27B Q4 via llama.cpp RPC across two machines, an RX 9060 XT 16GB and an RTX 5060 Ti 16GB, at 15-18 t/s with a 32k context. Setup is llama.cpp RPC with Q4 weights and a 32k context, split over the two 16GB cards. The user asks whether Qwen3.8 Flash-Next can be run by adding CPU-only RPC workers on the same machines to offload to their 32GB and 64GB of system RAM.

Nov 18, 2026

Qwen3.8 27B Swift-1.5

AMD RX 9060 XT 16GB · llama.cpp · 98,304 ctx

Tone: positiveAMD hardware
generation:
20-29 tokens/s
quant:
IQ3_S (GGUF)
kv:
q5_0/q4_1
codingagentictool-usevision

User reports running Swift-1.5-Qwen3.8-27B at IQ3_S on an RX 9060 XT 16GB, with eval in the mid 20s t/s and prompt processing between 550 and 231 t/s. Setup is llama.cpp (llama-server) with MTP draft speculation, q5_0 K and q4_1 V caches, 98304 context, all layers on the GPU and the mmproj kept on the CPU. Draft acceptance was around 0.6-0.8. A web-search agent request took 2m 10s end to end; the user has seen mid-40s eval at other settings. They ask whether to shrink context, add draft KV quantisation, and how to handle vision.

Nov 5, 2026
Tone: mixedAMD hardware
generation:
45.5 tokens/s
prompt processing (prefill):
161.9 tokens/s
quant:
Q2_0 (GGUF)
kv:
int8
chat

User reports Qwen3.8-Flash-Next Q2_0 at 45.5 t/s decode and 161.9 t/s prefill (pp4k) on an RX 9060 XT 16GB with 32GB DDR4, but says prefill is usually under 150 t/s and asks how to fix it. Setup is Strata 0.1.52 (HIP backend, Windows) with a 64K context and int8 KV cache; the 37.6 GB GGUF exceeds the card's VRAM, so weights run partly from system RAM. Strata's tuner ran 501.5 s and confirmed the defaults; two tuning arms were skipped for lack of free memory (25.6 GiB free, 28.4 GiB needed).

Oct 28, 2026
Tone: positiveAMD hardware
generation:
40-55 tokens/s
quant:
IQ3_S (GGUF)
kv:
Q8
coding

User reports running Qwen 3.8 Flash-Next IQ3_S and Swift 1.5 IQ3_XXS on an RX 9060 XT 16GB with a 7800X3D and 64GB RAM. Setup is Strata, with Flash-Next at a 130K context window and Q8 KV cache, and Swift 1.5 at 262K context and Q4 KV cache. Token generation stayed between 40-55 tk/s across the whole context window for both models. Prompt processing was around 800 tk/s on resumed sessions and around 900 tk/s during compaction. Neither model could build the requested Figma plugin in one shot, but the user is happy with performance and plans to stay on the 9060 XT.

Oct 25, 2026

Qwen3.6 35B (3B active)

AMD RX 9060 XT 16GB · PolyStrata-HIP · 31,296 ctx

Tone: positiveAMD hardware
generation:
70.7 tokens/s
prompt processing (prefill):
1326.0 tokens/s
quant:
UD-Q3_K_M (GGUF)
kv:
FP16

User reports Qwen3.6-35B-A3B at 70.7 tok/s generation on a 31,296-token prompt on an RX 9060 XT 16GB with a Ryzen 5 5600X and 32GB RAM on Windows 11. Setup is the PolyStrata-HIP fork of the strata-poly GGUF engine with Unsloth's UD-Q3_K_M quant, FP16 KV cache and MTP speculation enabled; experts not resident in VRAM are computed on the CPU from system RAM. Prefill on that run was 1,326 tok/s. Shorter warm prompts reached 93.4 tok/s at 2,068 tokens and 85.8 tok/s at 8,235 tokens, while a 45,355-token prompt gave 61.9 tok/s. With Q8_0 KV and 262,144 tokens of allocated capacity, a 400-token response ran at 33.8 tok/s capped at 2,000 resident experts versus 47.6 tok/s uncapped with 5,097 resident. Streaming KV through pinned RAM at roughly 261K tokens dropped generation to 3.64 tok/s.

Oct 18, 2026

Qwen3.8 27B

AMD RX 9060 XT 16GB · llama.cpp · 20,000 ctx

Tone: positiveAMD hardware
generation:
42.7 tokens/s
prompt processing (prefill):
658.0 tokens/s
quant:
IQ4_XS (GGUF)
kv:
Q4/Q8
mtp (multi-token prediction):
on

User reports Qwen 3.8 27B at 42.7 t/s generation and 658 t/s prefill at 20k context on a single RX 9060 XT 16GB. Setup is a fork of llama.cpp (achyudh/llama.cpp) with an unsloth IQ4_XS GGUF, Q4 KV values with Q8 keys, MTP plus n-gram prediction, and KV cache streaming; 24GB of DDR5 system RAM, 16GB of it used for this model. At 200k context the user reports 35 t/s generation and 300 t/s prefill, with a 262k context target. The user notes the build needed PCIe atomics fixes.

Oct 18, 2026
AMD hardware
generation:
66.0 tokens/s
quant:
UD-Q4_K_XL (GGUF)
kv:
q8_0

User reports Qwen3.6-35B-A3B at 66.04 tokens/s on an AMD Radeon RX 9060 XT 16 GB with 32 GB of system RAM. Setup is llama.cpp (Vulkan backend) with UD-Q4_K_XL GGUF weights, q8_0 KV cache, 40k context, and MTP speculative decoding drafting up to 3 tokens per step. The 35B MoE model does not fit in 16 GB of VRAM, so the expert weights of the first 20 layers run on the CPU. Run on a Ryzen 7 5800X3D desktop under SteamOS, single slot, with flash attention and prefix cache reuse enabled.

Oct 6, 2026
AMD hardware
generation:
30.0 tokens/s
quant:
IQ3_S (GGUF)

User asks whether Qwen3.8 Flash-Next can run on an RX 9060 XT 16GB with 32GB DDR5-6000. They currently run Swift-1.5-Qwen3.8 at IQ3_S at 30 t/s on the same machine.

Oct 3, 2026
AMD hardware
generation:
50.0 tokens/s
prompt processing (prefill):
850.0 tokens/s
quant:
IQ3_S (GGUF)

User reports 850 t/s prefill and 50 t/s generation with MTP at temperature 0 on an AMD RX 9060 XT 16GB, running Qwen3.8-27B-GSQ-RCO IQ3_S in a custom inference engine. MTP is used for the generation figure; the user notes MTP with temperature above 0 is not developed yet. User asks for ideas to systematically test the engine, having already run KL divergence against BF12 on CPU, bit correctness checks, needle-in-a-haystack at 25/50/75/90% key positions with distractors (also against llama.cpp), and HumanEval (92/93 passed so far).

Oct 3, 2026
AMD hardware
generation:
33.5 tokens/s
prompt processing (prefill):
1210.3 tokens/s
quant:
Q4_K_M (GGUF)

User benchmarks Qwen 2.5-Coder 14B Instruct Q4_K_M at 33.51 t/s generation and 1210.29 t/s prompt processing on an AMD RX 9060 XT 16GB via Vulkan. Setup is llama.cpp build c4ae9a88f8 with -ngl 99 and -fa 1; the same model on ROCm reaches 30.79 t/s generation and 1211.32 t/s prompt processing. A Qwen 3.5 9B Q4_K_M run reaches 50.15 t/s generation and 1904.16 t/s prompt processing on Vulkan, and a 14B quant sweep gives about 32, 28 and 20 tok/s for Q4_K_M, Q5_K_M and Q8_0.

Sep 29, 2026

Ornith1.5 9B

AMD RX 9060 XT 16GB · llama.cpp · 262,144 ctx

Tone: positiveAMD hardware
generation:
36.0 tokens/s
prompt processing (prefill):
950.0 tokens/s
quant:
Q6_K (GGUF)
kv:
Q8
codingagentic

User reports Ornith-1.5-9B at about 36 t/s generation and about 950 t/s prompt eval on an AMD RX 9060 XT 16GB with llama.cpp. Throughput drops to about 25 t/s generation and about 500 t/s prompt eval during long tasks. The run lasted about 3.5 hours on a coding agent task. The user contrasts this with Qwen 3.8 27B, which was frustratingly slow on the same hardware.

Sep 7, 2026