2 × RX 9070 LLM benchmarks

13 results · 13 measurements · 1 source

Explore all results Image benchmarks Submit a result

Device specifications

Variant	Memory	Memory type	Bus	Bandwidth	FP16 matrix	INT8 matrix
RX 9070 ↗	16 GB	GDDR6	256-bit	640 GB/s	145 TFLOPS	289 TOPS

Manufacturer specifications. Shared system RAM is not dedicated VRAM. Unreported values remain —; measured LLM results retain their reported configuration.

Selected reported tests

13 of 13 results

Source-reported results, selected across reports by documentation quality. Match configurations before comparing values.


View ReportGeneric LLM	Qwen3.8-27BUD-Q4_K_XLWeights ↗	Token speed	—	—	22.1 tok/sGeneration · per request	2 × RX 9070Multi-GPU · split unknown · 16 GB VRAM/GPU Configuration Memory 16 GB VRAM/GPU OS Not reported Engine llama.cpp Backend Vulkan Harness Contributor local greedy streaming harness Prompt / output ? / ? tokens Context 262144 Concurrency 1 Date Not reported Full record →
View ReportGeneric LLM	Qwen3.8-27BUD-Q4_K_XLWeights ↗	Token speed	—	—	21 tok/sGeneration · per request	2 × RX 9070Multi-GPU · split unknown · 16 GB VRAM/GPU Configuration Memory 16 GB VRAM/GPU OS Not reported Engine llama.cpp Backend Vulkan Harness Contributor local greedy streaming harness Prompt / output ? / ? tokens Context 262144 Concurrency 1 Date Not reported Full record →
View ReportGeneric LLM	Qwen3.8-27BUD-Q4_K_XLWeights ↗	Token speed	—	—	41.6 tok/sGeneration · median · per request	2 × RX 9070Multi-GPU · split unknown · 16 GB VRAM/GPU Configuration Memory 16 GB VRAM/GPU OS Not reported Engine llama.cpp Backend Vulkan Harness Contributor local greedy streaming harness Prompt / output ? / ? tokens Context 262144 Concurrency 1 Date Not reported Full record →
View ReportGeneric LLM	Qwen3.8-27BUD-Q4_K_XLWeights ↗	Token speed	—	—	37.2 tok/sGeneration · median · per request	2 × RX 9070Multi-GPU · split unknown · 16 GB VRAM/GPU Configuration Memory 16 GB VRAM/GPU OS Not reported Engine llama.cpp Backend Vulkan Harness Contributor local greedy streaming harness Prompt / output ? / ? tokens Context 262144 Concurrency 1 Date Not reported Full record →
View ReportGeneric LLM	Qwen3.8-27BUD-Q4_K_XLWeights ↗	Token speed	—	—	28 tok/sGeneration · median · per request	2 × RX 9070Multi-GPU · split unknown · 16 GB VRAM/GPU Configuration Memory 16 GB VRAM/GPU OS Not reported Engine llama.cpp Backend Vulkan Harness Contributor local greedy streaming harness Prompt / output ? / ? tokens Context 262144 Concurrency 1 Date Not reported Full record →
View ReportGeneric LLM	Qwen3.8-27BUD-Q4_K_XLWeights ↗	Token speed	—	—	42.9 tok/sGeneration · median · per request	2 × RX 9070Multi-GPU · split unknown · 16 GB VRAM/GPU Configuration Memory 16 GB VRAM/GPU OS Not reported Engine llama.cpp Backend Vulkan Harness Contributor local greedy streaming harness Prompt / output ? / ? tokens Context 262144 Concurrency 1 Date Not reported Full record →
View ReportGeneric LLM	Qwen3.8-27BUD-Q4_K_XLWeights ↗	Token speed	—	—	38.5 tok/sGeneration · median · per request	2 × RX 9070Multi-GPU · split unknown · 16 GB VRAM/GPU Configuration Memory 16 GB VRAM/GPU OS Not reported Engine llama.cpp Backend Vulkan Harness Contributor local greedy streaming harness Prompt / output ? / ? tokens Context 262144 Concurrency 1 Date Not reported Full record →
View ReportGeneric LLM	Qwen3.8-27BUD-Q4_K_XLWeights ↗	Token speed	—	—	27.4 tok/sGeneration · median · per request	2 × RX 9070Multi-GPU · split unknown · 16 GB VRAM/GPU Configuration Memory 16 GB VRAM/GPU OS Not reported Engine llama.cpp Backend Vulkan Harness Contributor local greedy streaming harness Prompt / output ? / ? tokens Context 262144 Concurrency 1 Date Not reported Full record →
View ReportGeneric LLM	Qwen3.8-27BUD-Q4_K_XLWeights ↗	Token speed	—	—	38.3 tok/sGeneration · per request	2 × RX 9070Multi-GPU · split unknown · 16 GB VRAM/GPU Configuration Memory 16 GB VRAM/GPU OS Not reported Engine llama.cpp Backend Vulkan Harness Contributor local greedy streaming harness Prompt / output ? / ? tokens Context 262144 Concurrency 1 Date Not reported Full record →
View ReportGeneric LLM	Qwen3.8-27BUD-Q4_K_XLWeights ↗	Token speed	—	—	36.6 tok/sGeneration · per request	2 × RX 9070Multi-GPU · split unknown · 16 GB VRAM/GPU Configuration Memory 16 GB VRAM/GPU OS Not reported Engine llama.cpp Backend Vulkan Harness Contributor local greedy streaming harness Prompt / output ? / ? tokens Context 262144 Concurrency 1 Date Not reported Full record →
View ReportGeneric LLM	Qwen3.8-27BUD-Q4_K_XLWeights ↗	Token speed	—	—	28.9 tok/sGeneration · per request	2 × RX 9070Multi-GPU · split unknown · 16 GB VRAM/GPU Configuration Memory 16 GB VRAM/GPU OS Not reported Engine llama.cpp Backend Vulkan Harness Contributor local greedy streaming harness Prompt / output ? / ? tokens Context 262144 Concurrency 1 Date Not reported Full record →
View ReportGeneric LLM	Qwen3.8-27BUD-Q4_K_XLWeights ↗	Token speed	—	—	40.7 tok/sGeneration · per request	2 × RX 9070Multi-GPU · split unknown · 16 GB VRAM/GPU Configuration Memory 16 GB VRAM/GPU OS Not reported Engine llama.cpp Backend Vulkan Harness Contributor local greedy streaming harness Prompt / output ? / ? tokens Context 262144 Concurrency 1 Date Not reported Full record →
View ReportGeneric LLM	Qwen3.8-27BUD-Q4_K_XLWeights ↗	Token speed	—	—	35.5 tok/sGeneration · per request	2 × RX 9070Multi-GPU · split unknown · 16 GB VRAM/GPU Configuration Memory 16 GB VRAM/GPU OS Not reported Engine llama.cpp Backend Vulkan Harness Contributor local greedy streaming harness Prompt / output ? / ? tokens Context 262144 Concurrency 1 Date Not reported Full record →

Explore all 13 results →

Models and software in this collection

Model families: Qwen3.8

Engines: llama.cpp

Methodology and evidence standards · Download the research dataset

2 × RX 9070 LLM benchmarks

Selected reported tests

LLMs benchmarked on the RX 9070