AMD-Pro-BenchCommunity

13,812 benchmarks in 32 GPU combinations documented

Qwen3.5-0.8B on AMD GPUs

14 results · 4 sources · 18 measurements

Explore all results

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

Documented results

14 selected tests
View
ReportLocalMaxxing		Qwen3.5-0.8BQ8_0Weights ↗Token speed—
20,661.62 tok/sPrefill · unknown
346.22 tok/sGeneration · unknown
1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPU
Configuration
Memory
24 GB VRAM/GPU
OS
Ubuntu 24.04.4 LTS
Engine
llama.cpp
Backend
Not reported
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
512 / 128 tokens
Context
512
Concurrency
Not reported
Date
2026-05-30
Full record →
View
ReportLocalMaxxing		Qwen3.5-0.8BMQ4Model ref. ↗Token speed——
291.4 tok/sGeneration · median · per request
1 × Ryzen AI Max+ 395Single GPU · Unified memory
Configuration
Memory
Unified memory
OS
Ubuntu 26.04
Engine
hipfire
Backend
rocm
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
13 / 100 tokens
Context
128
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		Qwen3.5-0.8BMQ4Model ref. ↗Token speed——
563.53 tok/sGeneration · median · per request
1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 26.04
Engine
hipfire
Backend
rocm
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
13 / 100 tokens
Context
128
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		Qwen3.5-0.8BMQ4Model ref. ↗Token speed——
545.27 tok/sGeneration · median · per request
1 × RX 9070 XTSingle GPU · 16 GB VRAM/GPU
Configuration
Memory
16 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
hipfire
Backend
rocm
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
13 / 100 tokens
Context
128
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		Qwen3.5-0.8BMQ4Model ref. ↗Token speed——
550.16 tok/sGeneration · per request
1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPU
Configuration
Memory
24 GB VRAM/GPU
OS
Ubuntu 26.04
Engine
hipfire
Backend
Not reported
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
13 / 100 tokens
Context
128
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		Qwen3.5-0.8BMQ4Model ref. ↗Latency1 concurrent request
69 msTime to first token · Per request
——1 × Ryzen AI Max+ 395Single GPU · Unified memory
Configuration
Memory
Unified memory
OS
Ubuntu 26.04
Engine
hipfire
Backend
rocm
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
? / ? tokens
Context
128
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		Qwen3.5-0.8BMQ4Model ref. ↗Token speed——
562.39 tok/sGeneration · median · per request
1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 26.04
Engine
hipfire
Backend
rocm
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
13 / 100 tokens
Context
128
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		Qwen3.5-0.8BMQ4Model ref. ↗Latency1 concurrent request
67 msTime to first token · Per request
——1 × RX 9070 XTSingle GPU · 16 GB VRAM/GPU
Configuration
Memory
16 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
hipfire
Backend
rocm
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
? / ? tokens
Context
128
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		Qwen3.5-0.8BMQ4Model ref. ↗Token speed——
562.03 tok/sGeneration · median · per request
1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 26.04
Engine
hipfire
Backend
rocm
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
13 / 100 tokens
Context
128
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		Qwen3.5-0.8BMQ4Model ref. ↗Token speed——
554.49 tok/sGeneration · median · per request
1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 26.04
Engine
hipfire
Backend
rocm
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
13 / 100 tokens
Context
128
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		Qwen3.5-0.8BMQ4Model ref. ↗Latency1 concurrent request
42 msTime to first token · Per request
——1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 26.04
Engine
hipfire
Backend
rocm
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
? / ? tokens
Context
128
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		Qwen3.5-0.8BMQ4Model ref. ↗Latency1 concurrent request
44 msTime to first token · Per request
——1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 26.04
Engine
hipfire
Backend
rocm
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
? / ? tokens
Context
128
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		Qwen3.5-0.8BMQ4Model ref. ↗Latency1 concurrent request
43 msTime to first token · Per request
——1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 26.04
Engine
hipfire
Backend
rocm
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
? / ? tokens
Context
128
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		Qwen3.5-0.8BMQ4Model ref. ↗Latency1 concurrent request
45 msTime to first token · Per request
——1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 26.04
Engine
hipfire
Backend
rocm
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
? / ? tokens
Context
128
Concurrency
1
Date
2026-08-10
Full record →
Quantizations and software

Quantizations: MQ4, Q8_0
Engines: hipfire, llama.cpp

Explore all 14 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 7900 XTX · Ryzen AI Max+ 395