Will It Run AI

Can Hermes 4.3 36B run on NVIDIA A800 80GB?

YES — Runs Great

C50Usable
Estimated from fit model

Hermes 4.3 36B needs ~35.4 GB VRAM. NVIDIA A800 80GB has 80.0 GB. With Q4_K_M quantization, expect ~69 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: Balanced
Share:

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 35.4 GB, 68.7 tok/s, Runs well
35.4 GB required80.0 GB available
44% VRAM used

Fit status

Runs well

Decode

68.7 tok/s

TTFT

2817 ms

Safe context

185K

Memory

35.4 GB / 80.0 GB

Memory breakdown

Weights22.0 GB
KV Cache4.2 GB
Runtime1.2 GB
Headroom8.0 GB

See how fast it feels

See how fast it feelsHermes 4.3 36B on NVIDIA A800 80GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step. Given information: - Speed = 60 mph (miles per hour) - Time = 2.5 hours Formula: Distance = Speed x Time Calculation: Distance = 60 mph x 2.5 h = 150 miles The train travels 150 miles. Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time. Breakdown: - First half: 1.25 hours at 60 mph = 75 miles - Stop: 20 minutes (no distance) - Second half: 1.25 hours at 60 mph = 75 miles Total distance: 150 miles (same) Total time: 2.5 h + 0.33 h = 2.83 hours Average speed: 150 / 2.83 = 53 mph The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 68.7 tok/s decode · 2.8s TTFT (warm) · 172 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatCRuns well68.7 tok/s1536 ms185K
CodingCRuns well68.7 tok/s2817 ms185K
Agentic CodingCRuns well68.7 tok/s4097 ms185K
ReasoningCRuns well68.7 tok/s3329 ms185K
RAGCRuns well68.7 tok/s5122 ms185K

Quantization options

How Hermes 4.3 36B (36B params) fits at each quantization level on NVIDIA A800 80GB (80.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
14.0 GB
LowC41
Q3_K_S
3
17.6 GB
LowC41
NVFP4
4
20.2 GB
MediumC42
Q4_K_M
4
22.0 GB
MediumC42
Q5_K_M
5
25.9 GB
HighC43
Q6_K
6
29.5 GB
HighC44
Q8_0Best for your GPU
8
38.5 GB
Very HighC46
F16
16
73.8 GB
MaximumF0

Get started

Copy-paste commands to run Hermes 4.3 36B on your machine.

Run

lms load hf-nousresearch--hermes-4-3-36b-gguf && lms server start

Frequently asked questions

Can NVIDIA A800 80GB run Hermes 4.3 36B?

Yes, NVIDIA A800 80GB can run Hermes 4.3 36B with a C grade (Runs well). Expected decode speed: 68.7 tok/s.

How much VRAM does Hermes 4.3 36B need?

Hermes 4.3 36B (36B parameters) requires approximately 35.4 GB of memory with Q4_K_M quantization.

What is the best quantization for Hermes 4.3 36B?

The recommended quantization for Hermes 4.3 36B is Q4_K_M, which balances quality and memory efficiency.

What speed will Hermes 4.3 36B run at on NVIDIA A800 80GB?

On NVIDIA A800 80GB, Hermes 4.3 36B achieves approximately 68.7 tokens per second decode speed with a time-to-first-token of 2817ms using Q4_K_M quantization.

Can NVIDIA A800 80GB run Hermes 4.3 36B for coding?

For coding workloads, Hermes 4.3 36B on NVIDIA A800 80GB receives a C grade with 68.7 tok/s and 185K context.

What context window can Hermes 4.3 36B use on NVIDIA A800 80GB?

On NVIDIA A800 80GB, Hermes 4.3 36B can safely use up to 185K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for NVIDIA A800 80GBSee all hardware for Hermes 4.3 36B
Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/hf-nousresearch--hermes-4-3-36b-gguf-on-a800-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: