AMD-Pro-BenchCommunity

13,812 benchmarks in 32 GPU combinations documented

granite-3.0-3b-a800m-instruct on AMD GPUs

30 results · 4 sources · 30 measurements

Explore all results

Grouped by reported model identity. Exact weights, quantizations and software can differ. How results are reviewed

Documented results

24 selected tests
View
ReportGeneric LLM		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed——
271.37 tok/sGeneration · mean · per request
1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
llama.cpp
Backend
Vulkan / Mesa RADV
Harness
Not reported
Prompt / output
? / 128 tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-18
Full record →
View
ReportGeneric LLM		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed——
193.36 tok/sGeneration · mean · per request
1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
llama.cpp
Backend
ROCm 7.0.0
Harness
Not reported
Prompt / output
? / 128 tokens
Context
Not reported
Concurrency
Not reported
Date
2026-05-14
Full record →
View
Reportllama-bench		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed——
312.11 tok/sGeneration · mean · per request
1 × RX 9070 XTSingle GPU · 16 GB VRAM/GPU
Configuration
Memory
16 GB VRAM/GPU
OS
Ubuntu 26.04 LTS / Linux 7.0
Engine
llama.cpp
Backend
Vulkan
Harness
Phoronix Test Suite / llama-bench
Prompt / output
0 / 128 tokens
Context
Not reported
Concurrency
Not reported
Date
2026-06-01
Full record →
View
Reportllama-bench		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed—
10,608.73 tok/sPrefill · mean · per request
—1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPU
Configuration
Memory
24 GB VRAM/GPU
OS
Ubuntu 26.04 / Linux7.0
Engine
llama.cpp
Backend
Vulkan
Harness
Phoronix Test Suite / llama-bench
Prompt / output
2048 / 0 tokens
Context
Not reported
Concurrency
1
Date
Not reported
Full record →
View
ReportGeneric LLM		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed——
180.05 tok/sGeneration · mean · per request
1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
llama.cpp
Backend
HIP / ROCm 7.1
Harness
Not reported
Prompt / output
? / 128 tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-18
Full record →
View
ReportGeneric LLM		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed——
190.13 tok/sGeneration · mean · per request
1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
llama.cpp
Backend
ROCm 7.2.3
Harness
Not reported
Prompt / output
? / 128 tokens
Context
Not reported
Concurrency
Not reported
Date
2026-05-14
Full record →
View
Reportllama-bench		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed——
303.7 tok/sGeneration · mean · per request
1 × RX 9070Single GPU · 16 GB VRAM/GPU
Configuration
Memory
16 GB VRAM/GPU
OS
Ubuntu 26.04 LTS / Linux 7.0
Engine
llama.cpp
Backend
Vulkan
Harness
Phoronix Test Suite / llama-bench
Prompt / output
0 / 128 tokens
Context
Not reported
Concurrency
Not reported
Date
2026-06-01
Full record →
View
Reportllama-bench		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed—
9,469.95 tok/sPrefill · mean · per request
—1 × RX 7900 XTSingle GPU · 20 GB VRAM/GPU
Configuration
Memory
20 GB VRAM/GPU
OS
Ubuntu 26.04 / Linux7.0
Engine
llama.cpp
Backend
Vulkan
Harness
Phoronix Test Suite / llama-bench
Prompt / output
2048 / 0 tokens
Context
Not reported
Concurrency
1
Date
Not reported
Full record →
View
ReportGeneric LLM		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed—
10,460.35 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
llama.cpp
Backend
Vulkan / Mesa RADV
Harness
Not reported
Prompt / output
512 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-18
Full record →
View
ReportGeneric LLM		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed—
13,041.98 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
llama.cpp
Backend
ROCm 7.0.0
Harness
Not reported
Prompt / output
512 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-05-14
Full record →
View
Reportllama-bench		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed——
254.58 tok/sGeneration · mean · per request
1 × RX 9070 GRESingle GPU · 12 GB VRAM/GPU
Configuration
Memory
12 GB VRAM/GPU
OS
Ubuntu 26.04 LTS / Linux 7.0
Engine
llama.cpp
Backend
Vulkan
Harness
Phoronix Test Suite / llama-bench
Prompt / output
0 / 128 tokens
Context
Not reported
Concurrency
Not reported
Date
2026-06-01
Full record →
View
Reportllama-bench		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed—
8,104.8 tok/sPrefill · mean · per request
—1 × RX 7900 GRESingle GPU · 16 GB VRAM/GPU
Configuration
Memory
16 GB VRAM/GPU
OS
Ubuntu 26.04 / Linux7.0
Engine
llama.cpp
Backend
Vulkan
Harness
Phoronix Test Suite / llama-bench
Prompt / output
2048 / 0 tokens
Context
Not reported
Concurrency
1
Date
Not reported
Full record →
View
ReportGeneric LLM		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed—
4,241.89 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
llama.cpp
Backend
HIP / ROCm 7.1
Harness
Not reported
Prompt / output
512 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-18
Full record →
View
ReportGeneric LLM		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed—
12,368.92 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
llama.cpp
Backend
ROCm 7.2.3
Harness
Not reported
Prompt / output
512 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-05-14
Full record →
View
Reportllama-bench		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed—
12,561.84 tok/sPrefill · mean · per request
—1 × RX 9070 XTSingle GPU · 16 GB VRAM/GPU
Configuration
Memory
16 GB VRAM/GPU
OS
Ubuntu 26.04 LTS / Linux 7.0
Engine
llama.cpp
Backend
Vulkan
Harness
Phoronix Test Suite / llama-bench
Prompt / output
2048 / 0 tokens
Context
Not reported
Concurrency
Not reported
Date
2026-06-01
Full record →
View
Reportllama-bench		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed—
6,806.75 tok/sPrefill · mean · per request
—1 × RX 7800 XTSingle GPU · 16 GB VRAM/GPU
Configuration
Memory
16 GB VRAM/GPU
OS
Ubuntu 26.04 / Linux7.0
Engine
llama.cpp
Backend
Vulkan
Harness
Phoronix Test Suite / llama-bench
Prompt / output
2048 / 0 tokens
Context
Not reported
Concurrency
1
Date
Not reported
Full record →
View
ReportGeneric LLM		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed—
10,165.05 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
llama.cpp
Backend
Vulkan / Mesa RADV
Harness
Not reported
Prompt / output
1024 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-18
Full record →
View
ReportGeneric LLM		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed—
12,483.74 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
llama.cpp
Backend
ROCm 7.0.0
Harness
Not reported
Prompt / output
1024 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-05-14
Full record →
View
Reportllama-bench		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed—
11,109.4 tok/sPrefill · mean · per request
—1 × RX 9070Single GPU · 16 GB VRAM/GPU
Configuration
Memory
16 GB VRAM/GPU
OS
Ubuntu 26.04 LTS / Linux 7.0
Engine
llama.cpp
Backend
Vulkan
Harness
Phoronix Test Suite / llama-bench
Prompt / output
2048 / 0 tokens
Context
Not reported
Concurrency
Not reported
Date
2026-06-01
Full record →
View
Reportllama-bench		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed——
368.03 tok/sGeneration · mean · per request
1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPU
Configuration
Memory
24 GB VRAM/GPU
OS
Ubuntu 26.04 / Linux7.0
Engine
llama.cpp
Backend
Vulkan
Harness
Phoronix Test Suite / llama-bench
Prompt / output
0 / 128 tokens
Context
Not reported
Concurrency
1
Date
Not reported
Full record →
View
ReportGeneric LLM		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed—
4,197.2 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
llama.cpp
Backend
HIP / ROCm 7.1
Harness
Not reported
Prompt / output
1024 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-18
Full record →
View
ReportGeneric LLM		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed—
12,067.26 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
llama.cpp
Backend
ROCm 7.2.3
Harness
Not reported
Prompt / output
1024 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-05-14
Full record →
View
Reportllama-bench		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed—
9,515.59 tok/sPrefill · mean · per request
—1 × RX 9070 GRESingle GPU · 12 GB VRAM/GPU
Configuration
Memory
12 GB VRAM/GPU
OS
Ubuntu 26.04 LTS / Linux 7.0
Engine
llama.cpp
Backend
Vulkan
Harness
Phoronix Test Suite / llama-bench
Prompt / output
2048 / 0 tokens
Context
Not reported
Concurrency
Not reported
Date
2026-06-01
Full record →
View
Reportllama-bench		granite-3.0-3b-a800m-instructQ8_0Model ref. ↗Token speed——
329.32 tok/sGeneration · mean · per request
1 × RX 7900 XTSingle GPU · 20 GB VRAM/GPU
Configuration
Memory
20 GB VRAM/GPU
OS
Ubuntu 26.04 / Linux7.0
Engine
llama.cpp
Backend
Vulkan
Harness
Phoronix Test Suite / llama-bench
Prompt / output
0 / 128 tokens
Context
Not reported
Concurrency
1
Date
Not reported
Full record →
Quantizations and software

Quantizations: Q8_0
Engines: llama.cpp

Explore all 30 results →

This is a selection across sources, not a ranking or a matched experiment. Reading benchmark reports

GPU benchmark pages: R9700 · RX 9070 XT · RX 9070 · RX 9070 GRE · RX 7900 XTX · RX 7900 XT · RX 7900 GRE · RX 7800 XT