AMD-Pro-BenchCommunity

13,812 benchmarks in 32 GPU combinations documented

LFM2.5-350M on AMD GPUs

29 results · 4 sources · 48 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
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed
1,181.64 tok/sThroughput · median · aggregate
——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
27 / 128 tokens
Context
4096
Concurrency
8
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed
3,283.31 tok/sThroughput · median · aggregate
——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
27 / 128 tokens
Context
4096
Concurrency
128
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed
3,669.85 tok/sThroughput · median · aggregate
——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
27 / 128 tokens
Context
4096
Concurrency
128
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed——
398.39 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
27 / 128 tokens
Context
4096
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed
777.02 tok/sThroughput · median · aggregate
——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
27 / 128 tokens
Context
4096
Concurrency
4
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed
1,291.87 tok/sThroughput · median · aggregate
——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
27 / 128 tokens
Context
4096
Concurrency
256
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed
1,876.92 tok/sThroughput · median · aggregate
——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
27 / 128 tokens
Context
4096
Concurrency
256
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed——
458.71 tok/sGeneration · unknown
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
27 / 128 tokens
Context
4096
Concurrency
2
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed
766.3 tok/sThroughput · median · aggregate
——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
27 / 128 tokens
Context
4096
Concurrency
4
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed
1,278.94 tok/sThroughput · median · aggregate
——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
27 / 128 tokens
Context
4096
Concurrency
128
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed
1,258.47 tok/sThroughput · median · aggregate
——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
27 / 128 tokens
Context
4096
Concurrency
256
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed——
858.4 tok/sGeneration · unknown
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
27 / 128 tokens
Context
4096
Concurrency
4
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed
439.1 tok/sThroughput · median · aggregate
——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
27 / 128 tokens
Context
4096
Concurrency
2
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed——
542.55 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
27 / 128 tokens
Context
4096
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed
1,237.75 tok/sThroughput · median · aggregate
——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
27 / 128 tokens
Context
4096
Concurrency
128
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed——
885.34 tok/sGeneration · unknown
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
27 / 128 tokens
Context
4096
Concurrency
4
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed——
343.07 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
27 / 128 tokens
Context
4096
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed——
542.15 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
27 / 128 tokens
Context
4096
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed——
520.78 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
27 / 128 tokens
Context
4096
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed——
1,470.77 tok/sGeneration · unknown
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
27 / 128 tokens
Context
4096
Concurrency
8
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed——
539.58 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
27 / 128 tokens
Context
4096
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed——
437.68 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
27 / 128 tokens
Context
4096
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Token speed——
538.35 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
27 / 128 tokens
Context
4096
Concurrency
1
Date
2026-08-10
Full record →
View
ReportLocalMaxxing		LFM2.5-350MMQ4Model ref. ↗Latency1 concurrent request
110 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
4096
Concurrency
1
Date
2026-08-10
Full record →
Quantizations and software

Quantizations: MQ4
Engines: hipfire

Explore all 29 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