ai-tier / edge

Hermes 3 Llama 3.1 8B on Pi 5

Snapshot · ai-tier

Raspberry Pi 5 · 16 GB RAMAll performance measurements are for this device.

Capability shows how well the model answers the benchmark questions. Speed, response time and memory are measured on Raspberry Pi 5 · 16 GB.

Capability summarises instruction following, tool calling and finding information in long prompts. Speed and memory refer to the Raspberry Pi 5. — means unavailable.
ModelCapability / 100Output tok/sPrompt tok/sFirst token · sTask time · sPeak memory · MiBParameters · B
Hermes 3 Llama 3.1 8BQ4_K_M · 4,096 context · reasoning off752.61137.41649,7818

Benchmark breakdown

Instruction following · IFEvalTool calling · BFCLFinding information · RULER
587098

Test configuration

Model publisher
Nous Research
Model parameters
8 billion total
Published input support
text (metadata; not device validation)
Quantization
Q4_K_M
Context capacity
4,096 tokens
Reasoning mode
off
CPU threads / parallel requests
4 / 1
Temperature / seed
0 / 42
Measurement date
2026-10-18T17:03:48.378011+00:00
Result ID
split-30468f73a575097c7221
Runtime revision
620d2225cc436ab0b001e3200e590e3b286ef9ab
Artifact repository / revision
bartowski/Hermes-3-Llama-3.1-8B-GGUF / 223c8e24dec0f863b6abe4c89bf20f6941b805e2
Artifact SHA256
44b5c529dffaf34657a4c44a7919e5958b4270fbd365eed3b87d3444b45a378a
Dataset revision
a0fc00b6a07455d1efb70cc19d5ca94c5923c5261a0b41095083a41a1592a1f6
Configuration identity
b547eb857931c62f2040fafd855461dc1a0b78fd077a32229c85942999db6ec2

Measurement limits

Speed tests read 256 input tokens and generate 128 output tokens, repeated ten times. The output speed test starts without a long conversation history. Answer time uses six fixed prompts with up to 128 output tokens, repeated three times. First-text time is measured from the application making the request. Peak memory includes the loaded model; it excludes other applications on the device. Longer prompts may need more memory. Capability uses a fixed selection of public questions, rather than the full official benchmarks.

Measured 2026-10-18T17:03:48.378011+00:00.