llamaperf

AMD RX 9060 XT 16GB

AMD · 16GB · 11 reports

Is this your card?

On the AMD RX 9060 XT 16GB, Qwen2.5 14B at 4-bit, the model most run on it, generates a median of 33.5 tokens per second from one plain run (community reports, as of 22 Nov 2026).

As of 22 Nov 2026, the models most run on the AMD RX 9060 XT 16GB, each one size at one quant level, with the median generation speed of its plain runs (one device, one request, no speculative decoding):

Bars are medians on one scale, 0 to 33.5 tokens/s. Press ▶ to watch text arrive at a row's speed.

Engines people use on it: llama.cpp 4 (reports) · Strata 1 (reports)

Run models on your AMD RX 9060 XT 16GB? Add your numbers.

Your coding agent can run a speed test on your machine and send it here with a free account. Or paste a result you've already posted.

Reported performance on the AMD RX 9060 XT 16GB

These reports mix GPU counts and memory setups, so a model listed here may have needed extra cards or CPU offloading. The calculator estimates which models fit in 16 GB of VRAM. Prompt processing is how fast the input is read, not how long you wait for the first word. How to measure time to first token.

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

Get a weekly email of new AMD RX 9060 XT 16GB reports and newly released models that fit it.

Email me new reports

Reported configurations

Individual observations from this page, not expected speeds or a ranking. Select a model to open its report, with the source and offloading conditions. Reported context may be a limit rather than actual input length.

Model / hardwareQuant / engineReported contextGeneration
Qwen3.8 125B (6B active) Flash-Next
AMD RX 9060 XT 16GB
Q2_0
Strata
65,53645.5 tokens/s
Qwen3.6 35B (3B active)
AMD RX 9060 XT 16GB
UD-Q3_K_M
PolyStrata-HIP
31,29670.7 tokens/s
Qwen3.8 27B
AMD RX 9060 XT 16GB
IQ4_XS
llama.cpp
20,00042.7 tokens/s
Qwen3.6 35B (3B active)
AMD RX 9060 XT 16GB
UD-Q4_K_XL
llama.cpp
40,96066.0 tokens/s
Qwen3.8 27B Swift-1.5
AMD RX 9060 XT 16GB
IQ3_S
Engine not reported
Not reported30.0 tokens/s
Qwen3.8 27B
AMD RX 9060 XT 16GB
IQ3_S
Engine not reported
Not reported50.0 tokens/s

Frequently asked

How fast is the AMD RX 9060 XT 16GB for local LLMs?

On the AMD RX 9060 XT 16GB, Qwen2.5 14B at 4-bit, the model most run on it, generates a median of 33.5 tokens per second from one plain run (community reports, as of 22 Nov 2026). Also reported: Qwen3.8 27B at 3-bit (30.0 t/s, one plain run).

What is the biggest model reported running on the AMD RX 9060 XT 16GB?

The largest model with a plain generation run on the AMD RX 9060 XT 16GB is Qwen3.8 27B at 3-bit (30.0 t/s, one plain run), as of 22 Nov 2026. Plain means one device, one request, no speculative decoding, so a run split across several cards does not count.