AMD-Pro-BenchCommunity

13,812 benchmarks in 32 GPU combinations documented

Nemotron-3-Nano-30B-A3B on R9700

295 results · 2 sources · 295 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		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed512 input tokens · 0 existing KV tokens—
2,349.2 tok/sPrefill · mean · per request
—2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (inferred; distribution unreported) (inferred)
Engine
llama.cpp
Backend
vulkan_amdvlk
Harness
llama-bench
Prompt / output
512 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed512 input tokens · 0 existing KV tokens—
2,000.18 tok/sPrefill · mean · per request
—2 × R9700Multi-GPU · split unknown · 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
vulkan_amdvlk
Harness
llama-bench
Prompt / output
512 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed128 output tokens · 0 existing KV tokens——
94.19 tok/sGeneration · mean · per request
2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (inferred; distribution unreported) (inferred)
Engine
llama.cpp
Backend
vulkan_amdvlk
Harness
llama-bench
Prompt / output
? / 128 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed128 output tokens · 0 existing KV tokens——
95.93 tok/sGeneration · mean · per request
2 × R9700Multi-GPU · split unknown · 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
vulkan_amdvlk
Harness
llama-bench
Prompt / output
? / 128 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed2,048 input tokens · 16,384 existing KV tokens—
1,421.57 tok/sPrefill · mean · per request
—2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (inferred; distribution unreported) (inferred)
Engine
llama.cpp
Backend
vulkan_amdvlk
Harness
llama-bench
Prompt / output
2048 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed2,048 input tokens · 16,384 existing KV tokens—
2,142.65 tok/sPrefill · mean · per request
—2 × R9700Multi-GPU · split unknown · 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
vulkan_amdvlk
Harness
llama-bench
Prompt / output
2048 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed32 output tokens · 16,384 existing KV tokens——
74.69 tok/sGeneration · mean · per request
2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (inferred; distribution unreported) (inferred)
Engine
llama.cpp
Backend
vulkan_amdvlk
Harness
llama-bench
Prompt / output
? / 32 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed32 output tokens · 16,384 existing KV tokens——
90.54 tok/sGeneration · mean · per request
2 × R9700Multi-GPU · split unknown · 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
vulkan_amdvlk
Harness
llama-bench
Prompt / output
? / 32 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed2,048 input tokens · 32,768 existing KV tokens—
710.37 tok/sPrefill · mean · per request
—2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (inferred; distribution unreported) (inferred)
Engine
llama.cpp
Backend
vulkan_amdvlk
Harness
llama-bench
Prompt / output
2048 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed2,048 input tokens · 32,768 existing KV tokens—
1,836.72 tok/sPrefill · mean · per request
—2 × R9700Multi-GPU · split unknown · 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
vulkan_amdvlk
Harness
llama-bench
Prompt / output
2048 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed32 output tokens · 32,768 existing KV tokens——
60.48 tok/sGeneration · mean · per request
2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (inferred; distribution unreported) (inferred)
Engine
llama.cpp
Backend
vulkan_amdvlk
Harness
llama-bench
Prompt / output
? / 32 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed32 output tokens · 32,768 existing KV tokens——
87.16 tok/sGeneration · mean · per request
2 × R9700Multi-GPU · split unknown · 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
vulkan_amdvlk
Harness
llama-bench
Prompt / output
? / 32 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed512 input tokens · 0 existing KV tokens—
1,758.38 tok/sPrefill · mean · per request
—2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (inferred; distribution unreported) (inferred)
Engine
llama.cpp
Backend
vulkan_radv
Harness
llama-bench
Prompt / output
512 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed2,048 input tokens · 65,536 existing KV tokens—
1,234.5 tok/sPrefill · mean · per request
—2 × R9700Multi-GPU · split unknown · 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
vulkan_amdvlk
Harness
llama-bench
Prompt / output
2048 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed128 output tokens · 0 existing KV tokens——
76.77 tok/sGeneration · mean · per request
2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (inferred; distribution unreported) (inferred)
Engine
llama.cpp
Backend
vulkan_radv
Harness
llama-bench
Prompt / output
? / 128 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed32 output tokens · 65,536 existing KV tokens——
82.19 tok/sGeneration · mean · per request
2 × R9700Multi-GPU · split unknown · 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
vulkan_amdvlk
Harness
llama-bench
Prompt / output
? / 32 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed2,048 input tokens · 16,384 existing KV tokens—
1,559.49 tok/sPrefill · mean · per request
—2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (inferred; distribution unreported) (inferred)
Engine
llama.cpp
Backend
vulkan_radv
Harness
llama-bench
Prompt / output
2048 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed512 input tokens · 0 existing KV tokens—
2,973.37 tok/sPrefill · mean · per request
—2 × R9700Multi-GPU · split unknown · 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
vulkan_radv
Harness
llama-bench
Prompt / output
512 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed32 output tokens · 16,384 existing KV tokens——
70.05 tok/sGeneration · mean · per request
2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (inferred; distribution unreported) (inferred)
Engine
llama.cpp
Backend
vulkan_radv
Harness
llama-bench
Prompt / output
? / 32 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed128 output tokens · 0 existing KV tokens——
85.19 tok/sGeneration · mean · per request
2 × R9700Multi-GPU · split unknown · 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
vulkan_radv
Harness
llama-bench
Prompt / output
? / 128 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed2,048 input tokens · 32,768 existing KV tokens—
1,158.36 tok/sPrefill · mean · per request
—2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (inferred; distribution unreported) (inferred)
Engine
llama.cpp
Backend
vulkan_radv
Harness
llama-bench
Prompt / output
2048 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed2,048 input tokens · 16,384 existing KV tokens—
3,240.01 tok/sPrefill · mean · per request
—2 × R9700Multi-GPU · split unknown · 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
vulkan_radv
Harness
llama-bench
Prompt / output
2048 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed32 output tokens · 32,768 existing KV tokens——
65.09 tok/sGeneration · mean · per request
2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (inferred; distribution unreported) (inferred)
Engine
llama.cpp
Backend
vulkan_radv
Harness
llama-bench
Prompt / output
? / 32 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
Reportllama-bench		Nemotron-3-Nano-30B-A3BUD-Q8_K_XLModel ref. ↗Token speed32 output tokens · 16,384 existing KV tokens——
82.47 tok/sGeneration · mean · per request
2 × R9700Multi-GPU · split unknown · 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
vulkan_radv
Harness
llama-bench
Prompt / output
? / 32 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
Quantizations and software

Quantizations: UD-Q4_K_XL, UD-Q8_K_XL
Engines: llama.cpp

Explore all 295 results →

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

GPU benchmark pages: R9700