llamaperf

AMD RX 7600 XT 16GB reports

4 reports. These are individual setups, not a controlled benchmark. AMD RX 7600 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 7600 XT 16GB · llama.cpp · 35,000 ctx

AMD hardware
generation:
30.0 tokens/s
prompt processing (prefill):
550.0 tokens/s
quant:
UD-Q4_K_XL (GGUF)
kv:
f16

User reports Qwen3.8 27B at 550 t/s prompt processing and 30 t/s generation on an RX 7600 XT 16GB plus RX 9060 XT 16GB, in a moderate context of 35k tokens. Setup is llama.cpp (latest git) with UD-Q4_K_XL GGUF weights, f16 KV cache, tensor split 60/40, flash attention on, and draft-MTP plus ngram-mod speculative decoding. ROCm was considerably faster than Vulkan. Adaptive KV streaming reached over 800 t/s prefill but limited the user to lower quantizations and left the second card unused. The user asks whether Strata or another fork would do better on this 32GB RAM system.

Nov 16, 2026

Qwen3.8 27B

AMD RX 7600 XT 16GB · llama.cpp · 114,688 ctx

Tone: positiveAMD hardware
quant:
GSQ-RCO-IQ3_XXS (GGUF)
kv:
Q4_0
mtp (multi-token prediction):
on
codingagentic

User benchmarks Qwen3.8 27B on an RX 7600 XT 16GB, completing 15/15 tasks with 1.000 correctness in 348.5 seconds. Setup is llama.cpp HIP ROCm with the GSQ-RCO-IQ3_XXS GGUF and a Q4_0 KV cache at 114,688 context, fully in VRAM with no CPU offload. The same benchmark also ran Ornith-1.5-9B (15/15, 0.983, 184.9s) and K2-Horizon-7B (11/15, 0.909, 498.1s); the user calls Qwen3.8 27B the undisputed winner for agentic coding.

Sep 23, 2026

Qwen3.8 27B

AMD RX 7600 XT 16GB · llama.cpp · 163,840 ctx

Tone: positiveAMD hardware
generation:
18.0 tokens/s
prompt processing (prefill):
141.0 tokens/s
quant:
IQ3_XXS (GGUF)
kv:
q8_0
mtp (multi-token prediction):
off
coding

User reports Qwen3.8 27B at 18 t/s decode and 141 t/s prefill on a 1.8k-token prompt, running on an AMD Radeon RX 7600 XT 16 GB at 163,840 context. Setup is llama.cpp llama-server build 10480 with the unsloth Qwen3.8-27B-UD-IQ3_XXS GGUF (10.2 GiB), q8_0 KV cache, flash attention on, and Vulkan (RADV) backend. The model is a hybrid architecture where only 16 of 64 layers keep a full KV cache, so KV is about 5.3 GiB at this context. With MTP on the same model runs about 24 t/s at 98k context and 39 t/s at 124k. The user notes 160k is a VRAM-math ceiling, not a quality claim, and that decode drops to about 6 t/s if the GPU spills to system RAM.

Sep 23, 2026

Muse 30B Glimmer

AMD RX 7600 XT 16GB · llama.cpp · 62,144 ctx

Tone: positiveAMD hardware
generation:
20.0 tokens/s
prompt processing (prefill):
308.0 tokens/s
quant:
UD-Q2-K-XL
coding

User reports Muse Glimmer 30B at about 308 t/s prompt processing and about 20 t/s generation on an RX 7600 XT 16GB. Setup is llama.cpp with ROCm, the UD-Q2-K-XL quant and DFlash speculative decoding. The run completed a coding task.

Sep 8, 2026