Laguna-XS-2.1 on AMD GPUs
5 results · 3 sources · 23 measurements
Grouped by reported model identity. Exact weights, quantizations and software can differ. How results are reviewed
Documented results
5 selected tests | | | | | | |
|---|
View
ReportLocalMaxxing | Laguna-XS-2.1Q4_K_MModel ref. ↗ | Token speed | — | 1,255 tok/sPrefill · median · unknown | 92.7 tok/sGeneration · median · unknown | 1 × Ryzen AI Max+ 395Single GPU · Unified memoryConfiguration- Memory
- Unified memory
- OS
- Ubuntu 24.04
- Engine
- llama.cpp
- Backend
- vulkan
- Harness
- LocalMaxxing community speed test; exact client where reported
- Prompt / output
- 1194 / 170 tokens
- Context
- 8192
- Concurrency
- Not reported
- Date
- 2026-08-11
Full record → |
|---|
View
ReportLocalMaxxing | Laguna-XS-2.1Q8_0Model ref. ↗ | Token speed | — | 1,754.32 tok/sPrefill · unknown | 100.32 tok/sGeneration · peak · unknown | 3 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPUConfiguration- Memory
- 32 GB VRAM/GPU
- OS
- Arch Linux
- Engine
- llama.cpp
- Backend
- vulkan
- Harness
- LocalMaxxing community speed test; exact client where reported
- Prompt / output
- 536 / 256 tokens
- Context
- 792
- Concurrency
- Not reported
- Date
- 2026-08-04
Full record → |
|---|
View
ReportLocalMaxxing | Laguna-XS-2.1Q8_0Model ref. ↗ | Token speed | — | 2,317.08 tok/sPrefill · unknown | 112.52 tok/sGeneration · unknown | 2 × RX 7900 XTXLayer split · 24 GB VRAM/GPUConfiguration- Memory
- 24 GB VRAM/GPU
- OS
- Arch Linux
- Engine
- llama.cpp
- Backend
- Not reported
- Harness
- LocalMaxxing community speed test; exact client where reported
- Prompt / output
- 536 / 256 tokens
- Context
- 32768
- Concurrency
- Not reported
- Date
- 2026-09-15
Full record → |
|---|
View
ReportLocalMaxxing | Laguna-XS-2.1Q4_K_MModel ref. ↗ | Token speed | — | 1,229.3 tok/sPrefill · median · unknown | 92 tok/sGeneration · median · unknown | 1 × Ryzen AI Max+ 395Single GPU · Unified memoryConfiguration- Memory
- Unified memory
- OS
- Ubuntu 24.04
- Engine
- llama.cpp
- Backend
- vulkan
- Harness
- LocalMaxxing community speed test; exact client where reported
- Prompt / output
- 1194 / 170 tokens
- Context
- 8192
- Concurrency
- Not reported
- Date
- 2026-08-11
Full record → |
|---|
View
ReportLocalMaxxing | Laguna-XS-2.1Q8_0Model ref. ↗ | Token speed | — | 2,069.76 tok/sPrefill · unknown | 136.8 tok/sGeneration · unknown | 2 × RX 7900 XTXLayer split · 24 GB VRAM/GPUConfiguration- Memory
- 24 GB VRAM/GPU
- OS
- Arch Linux
- Engine
- llama.cpp
- Backend
- Not reported
- Harness
- LocalMaxxing community speed test; exact client where reported
- Prompt / output
- 536 / 256 tokens
- Context
- 32768
- Concurrency
- Not reported
- Date
- 2026-09-15
Full record → |
|---|
Quantizations and software
Quantizations: Q4_K_M, Q8_0
Engines: llama.cpp
This is a selection across sources, not a ranking or a matched experiment. Reading benchmark reports
GPU benchmark pages: R9700 · RX 7900 XTX · Ryzen AI Max+ 395