llm workload · 1 runs on record

Hermes 3 Llama 3.1 8B (Q4_K_M)

NousResearch Hermes 3 Llama 3.1 8B (8B), Q4_K_M GGUF, batch 1, 4K context, measured on RTX 5090.

Primary metric: Tokens / sec (tok/s)

Reference prompts

Representative prompts for this workload. Exact prompts and harness settings still depend on the cited source for each record.

Prompt 1
Explain the relationship between attention heads and KV cache memory usage for a 7B-parameter transformer at 4K context.
Prompt 2
Write a 60-word product description for a mid-range AI workstation: 1× RTX 4090, 64GB DDR5, 2TB NVMe. Highlight one trade-off.
Prompt 3
List five concrete differences between INT4 weight-only quantization (Q4_K_M) and INT8 quantization (Q8_0) for inference.
Prompt 4
I have 12GB of VRAM and want to run a coding assistant locally. What model size and quantization fit, with what context length?
Prompt 5
Summarize the difference between greedy decoding and nucleus sampling in 3 short bullet points.

Reference runtime command

A representative invocation for reproducing this workload class. Source-specific runs may use adjacent runtimes unless the record says otherwise.

shell

OLLAMA_NUM_PARALLEL=1 ollama run hermes-3-llama-3.1-8b --verbose   # num_ctx 4096, batch 1

NousResearch Hermes 3 Llama 3.1 8B (8B) via Ollama 0.32.1, Q4_K_M GGUF, batch 1, 4K context, measured on RTX 5090 (Vast.ai). Throughput reported as the median Ollama eval rate.

Full leaderboard

Every record for Hermes 3 Llama 3.1 8B.

Top 10 leaderboard

Hermes 3 Llama 3.1 8B (Q4_K_M) · sorted by tokens / sec

1 entries

Full leaderboard

Click any row for detailed breakdown. Click column headers to sort.

	#	Device	Verif							Buy
	1	NVIDIA GeForce RTX 5090 32GBConsumer GPU NVIDIA·Q4_K_M·4K ctx	8	205tok/s	32 GB	575 W	$2.0k	0.36 tok/s/W	$0.10/M	Amazon

Sorted by Tokens / sec (high → low)Tip: $/1k tok is a 3-year amortization of MSRP at sustained throughput.

Cite this benchmark

Use this in your paper, blog post, or comparison table.

BibTeX

@misc{myaihardware_hermes-3-llama-3-1-8b-q4_2026,
  title  = {MyAI Bench: Hermes 3 Llama 3.1 8B (Q4_K_M)},
  author = {{MyAIHardware Contributors}},
  year   = {2026},
  url    = {https://www.myaihardware.com/benchmarks/workload/hermes-3-llama-3-1-8b-q4},
  note   = {Version 1.3, accessed 2026-08-30}
}

APA

MyAIHardware Contributors. (2026). MyAI Bench: Hermes 3 Llama 3.1 8B (Q4_K_M). MyAIHardware. Retrieved 2026-08-30, from https://www.myaihardware.com/benchmarks/workload/hermes-3-llama-3-1-8b-q4

MLA

MyAIHardware Contributors. "MyAI Bench: Hermes 3 Llama 3.1 8B (Q4_K_M)." MyAIHardware, 2026, https://www.myaihardware.com/benchmarks/workload/hermes-3-llama-3-1-8b-q4. Accessed 2026-08-30.

Plain text

MyAI Bench, Hermes 3 Llama 3.1 8B (Q4_K_M). MyAIHardware Contributors, 2026. Version 1.3. https://www.myaihardware.com/benchmarks/workload/hermes-3-llama-3-1-8b-q4 (accessed 2026-08-30).