Can Hermes 4.3 36B run on Gaudi 3 128GB?

YES — Runs Great

C48Usable

Estimated from fit model

Hermes 4.3 36B needs ~39.9 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~118 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced

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) — 39.9 GB, 117.9 tok/s, Runs well

39.9 GB required128.0 GB available

31% VRAM used

Fit status

Runs well

Decode

117.9 tok/s

TTFT

1641 ms

Safe context

350K

Memory

39.9 GB / 128.0 GB

Memory breakdown

Weights22.0 GB

KV Cache4.2 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsHermes 4.3 36B on Gaudi 3 128GB
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: 117.9 tok/s decode · 1.6s TTFT (warm) · 295 tok/s prefill

What limits this setup

The raw memory story may look fine, but the software ecosystem is still a constraint here.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

Best improvement path

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Runs well	117.9 tok/s	895 ms	350K
Coding	C	Runs well	117.9 tok/s	1641 ms	350K
Agentic Coding	C	Runs well	117.9 tok/s	2388 ms	350K
Reasoning	C	Runs well	117.9 tok/s	1940 ms	350K
RAG	C	Runs well	117.9 tok/s	2985 ms	350K

Inference speed

Hermes 4.3 36B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Hermes 4.3 36B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~55 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	54.7	Offloads
2× RX 7900 XTX 24GB	48 GB	Q4_K_M	53.5	Fits
2× RTX 4090 24GB	48 GB	Q4_K_M	28.1	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	27.3	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	27.3	Fits
2× RTX 3090 24GB	48 GB	Q4_K_M	25.8	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	25.4	Fits
4× RTX 3060 12GB	48 GB	Q4_K_M	22.7	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	21.1	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	20.0	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	17.2	Tight
RTX 4090 24GB	24 GB	Q4_K_M	16.6	Too big
RX 7900 XTX 24GB	24 GB	Q4_K_M	15.3	Too big
RTX 3090 24GB	24 GB	Q4_K_M	14.2	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	10.9	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	10.0	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	6.0	Too big
RTX 4070 12GB	12 GB	Q4_K_M	2.6	Too big
RTX 3060 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.0	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Hermes 4.3 36B (36B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	14.0 GB	Low	D38
Q3_K_S	3	17.6 GB	Low	D39
NVFP4	4	20.2 GB	Medium	D39
Q4_K_M	4	22.0 GB	Medium	D39
Q5_K_M	5	25.9 GB	High	D40
Q6_K	6	29.5 GB	High	C40
Q8_0	8	38.5 GB	Very High	C42
F16Best for your GPU	16	73.8 GB	Maximum	C48

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 Gaudi 3 128GB run Hermes 4.3 36B?

Yes, Gaudi 3 128GB can run Hermes 4.3 36B with a C grade (Runs well). Expected decode speed: 117.9 tok/s.

How much VRAM does Hermes 4.3 36B need?

Hermes 4.3 36B (36B parameters) requires approximately 39.9 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 Gaudi 3 128GB?

On Gaudi 3 128GB, Hermes 4.3 36B achieves approximately 117.9 tokens per second decode speed with a time-to-first-token of 1641ms using Q4_K_M quantization.

Can Gaudi 3 128GB run Hermes 4.3 36B for coding?

For coding workloads, Hermes 4.3 36B on Gaudi 3 128GB receives a C grade with 117.9 tok/s and 350K context.

What context window can Hermes 4.3 36B use on Gaudi 3 128GB?

On Gaudi 3 128GB, Hermes 4.3 36B can safely use up to 350K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

What should I upgrade first if Hermes 4.3 36B feels slow on Gaudi 3 128GB?

Prefer CUDA if you want the path of least resistance. If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Would CUDA be a better path than Gaudi 3 128GB for Hermes 4.3 36B?

Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.

See all results for Gaudi 3 128GB See 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-gaudi-3-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: