AMD-Pro-BenchCommunity

13,812 benchmarks in 32 GPU combinations documented

Llama-2-7B on AMD GPUs

422 results · 29 sources · 422 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
Reportllama-bench		Llama-2-7BQ4_0Model ref. ↗Token speed—
4,343.73 tok/sPrefill · mean · per request
—1 × RX 9070 XTSingle GPU · 16 GB VRAM/GPU
Configuration
Memory
16 GB VRAM/GPU
OS
Fedora 44 / kernel 7.1.3-201.fc44.x86_64
Engine
llama.cpp
Backend
Vulkan
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
Not reported
Date
2026-07-15
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Model ref. ↗Token speed512 input tokens · 0 output tokens · 0 existing KV tokens—
1,545.36 tok/sPrefill · mean · per request
—1 × Ryzen AI Max+ 395Single GPU · Unified memory
Configuration
Memory
Unified memory
OS
Fedora Linux 43 (Workstation Edition)
Engine
llama.cpp
Backend
ROCm / rocm-7_2_3
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2026-05-16
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Model ref. ↗Token speed—
2,641.07 tok/sPrefill · mean · per request
—1 × RX 9060 XTSingle GPU · 16 GB VRAM/GPU
Configuration
Memory
16 GB VRAM/GPU
OS
Arch Linux / kernel 7.2.5
Engine
llama.cpp
Backend
ROCm / HIP
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
Not reported
Date
2026-10-02
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Model ref. ↗Token speed—
2,844.8 tok/sPrefill · mean · per request
—1 × RX 9060 XTSingle GPU · 16 GB VRAM/GPU
Configuration
Memory
16 GB VRAM/GPU
OS
Arch Linux / kernel 7.2.5
Engine
llama.cpp
Backend
Vulkan
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
Not reported
Date
2026-10-02
Full record →
View
ReportGeneric LLM		Llama-2-7BQ4_0Model ref. ↗Token speed—
2,193.89 tok/sPrefill · mean · per request
—1 × W7900Single GPU
Configuration
Memory
Not reported
OS
Ubuntu 22.04 LTS HWE
Engine
llama.cpp
Backend
ROCm 6.0
Harness
Not reported
Prompt / output
3968 / ? tokens
Context
Not reported
Concurrency
1
Date
Not reported
Full record →
View
ReportGeneric LLM		Llama-2-7BQ4_0Weights ↗Token speed—
5,609.82 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Not reported
Engine
llama.cpp
Backend
Vulkan RADV
Harness
Not reported
Prompt / output
512 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-08-12
Full record →
View
ReportGeneric LLM		Llama-2-7BQ4_0Weights ↗Token speed—
5,583 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Not reported
Engine
llama.cpp
Backend
Vulkan RADV
Harness
Not reported
Prompt / output
512 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-08-14
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Model ref. ↗Token speed—
2,361.1 tok/sPrefill · mean · per request
—1 × RX 9070Single GPU · 16 GB VRAM/GPU
Configuration
Memory
16 GB VRAM/GPU
OS
Not reported
Engine
llama.cpp
Backend
ROCm / HIP
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
Not reported
Date
2025-08-17
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Model ref. ↗Token speed2,048 input tokens · 16,384 existing KV tokens—
843.75 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (inferred; distribution unreported) (inferred)
Engine
llama.cpp
Backend
rocm-7-nightly
Harness
llama-bench
Prompt / output
2048 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Model ref. ↗Token speed2,048 input tokens · 16,384 existing KV tokens—
1,135.56 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Fedora 42 — Linux 6.15.9-201.fc42.x86_64 (Sat Aug 2 11:37:34 UTC 2025)
Engine
llama.cpp
Backend
rocm6_4_4
Harness
llama-bench
Prompt / output
2048 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Weights ↗Token speed—
758.55 tok/sPrefill · mean · per request
—1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPU
Configuration
Memory
24 GB VRAM/GPU
OS
Arch Linux / Linux 6.12.61-1-lts
Engine
llama.cpp
Backend
Vulkan
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2025-12-11
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Weights ↗Token speed—
2,151.81 tok/sPrefill · mean · per request
—1 × RX 7800 XTSingle GPU · 16 GB VRAM/GPU
Configuration
Memory
16 GB VRAM/GPU
OS
Windows 10.
Engine
llama.cpp
Backend
ROCm / HIP
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2025-08-01
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Weights ↗Token speed—
2,109.38 tok/sPrefill · mean · per request
—1 × RX 7800 XTSingle GPU · 16 GB VRAM/GPU
Configuration
Memory
16 GB VRAM/GPU
OS
Windows (inferred) (inferred)
Engine
llama.cpp
Backend
ROCm / HIP
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2025-08-08
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Weights ↗Token speed—
2,967.12 tok/sPrefill · mean · per request
—1 × RX 7900 XTSingle GPU · 20 GB VRAM/GPU
Configuration
Memory
20 GB VRAM/GPU
OS
Linux
Engine
llama.cpp
Backend
ROCm / HIP
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2025-08-01
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Weights ↗Token speed—
1,099.64 tok/sPrefill · mean · per request
—1 × RX 7600 XTSingle GPU · 16 GB VRAM/GPU
Configuration
Memory
16 GB VRAM/GPU
OS
Linux 6.12.32
Engine
llama.cpp
Backend
ROCm / HIP
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2025-08-01
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Weights ↗Token speed—
3,243.15 tok/sPrefill · mean · per request
—1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPU
Configuration
Memory
24 GB VRAM/GPU
OS
Opensuse tumbleweed
Engine
llama.cpp
Backend
ROCm / HIP
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2025-08-05
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Weights ↗Token speed—
2,817.81 tok/sPrefill · mean · per request
—1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPU
Configuration
Memory
24 GB VRAM/GPU
OS
Arch Linux
Engine
llama.cpp
Backend
ROCm / HIP
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2025-09-17
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Weights ↗Token speed—
3,434.01 tok/sPrefill · mean · per request
—1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPU
Configuration
Memory
24 GB VRAM/GPU
OS
Windows 11 24H2 26100.4652
Engine
llama.cpp
Backend
ROCm / HIP
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2025-08-06
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Weights ↗Token speed—
3,386.75 tok/sPrefill · mean · per request
—1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPU
Configuration
Memory
24 GB VRAM/GPU
OS
Ubuntu 24.04.2
Engine
llama.cpp
Backend
ROCm / HIP
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2025-08-08
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Weights ↗Token speed—
3,473.24 tok/sPrefill · mean · per request
—1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPU
Configuration
Memory
24 GB VRAM/GPU
OS
Ubuntu 24.04.2
Engine
llama.cpp
Backend
ROCm / HIP
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2025-08-13
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Weights ↗Token speed—
3,875.83 tok/sPrefill · mean · per request
—1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPU
Configuration
Memory
24 GB VRAM/GPU
OS
CachyOS x86_64
Engine
llama.cpp
Backend
ROCm / HIP
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2026-08-23
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Weights ↗Token speed—
4,145.55 tok/sPrefill · mean · per request
—1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPU
Configuration
Memory
24 GB VRAM/GPU
OS
Windows 11 25H2 26200.9445
Engine
llama.cpp
Backend
ROCm / HIP
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2026-09-10
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Weights ↗Token speed—
3,692.87 tok/sPrefill · mean · per request
—1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPU
Configuration
Memory
24 GB VRAM/GPU
OS
CachyOS x86_64
Engine
llama.cpp
Backend
Vulkan
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2026-08-23
Full record →
View
Reportllama-bench		Llama-2-7BQ4_0Weights ↗Token speed—
3,726.99 tok/sPrefill · mean · per request
—1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPU
Configuration
Memory
24 GB VRAM/GPU
OS
Windows 11 25H2 26200.9445
Engine
llama.cpp
Backend
Vulkan
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2026-09-10
Full record →
Quantizations and software

Quantizations: Q4_0
Engines: llama.cpp

Explore all 422 results →

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

GPU benchmark pages: W7900 · R9700 · RX 9070 XT · RX 9070 · RX 9060 XT · RX 7900 XTX · RX 7900 XT · RX 7900 GRE · RX 7800 XT · RX 7600 XT · Ryzen AI Max+ 395