Can Falcon 40B Instruct run on NVIDIA GH200 96GB?

YES — Runs Great

A72Great

Estimated from fit model

Falcon 40B Instruct needs ~41.4 GB VRAM. NVIDIA GH200 96GB has 96.0 GB. With Q5_K_M quantization, expect ~125 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: 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

Q5_K_M (High quality) — 41.4 GB, 124.8 tok/s, Runs well

41.4 GB required96.0 GB available

43% VRAM used

Fit status

Runs well

Decode

124.8 tok/s

TTFT

1551 ms

Safe context

Memory

41.4 GB / 96.0 GB

Memory breakdown

Weights28.8 GB

KV Cache1.8 GB

Runtime1.2 GB

Headroom9.6 GB

See how fast it feels

See how fast it feelsFalcon 40B Instruct on NVIDIA GH200 96GB
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: 124.8 tok/s decode · 1.6s TTFT (warm) · 312 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

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs well	124.8 tok/s	846 ms	8K
Coding	A	Runs well	124.8 tok/s	1551 ms	8K
Agentic Coding	A	Runs well	124.8 tok/s	2257 ms	8K
Reasoning	A	Runs well	124.8 tok/s	1833 ms	8K
RAG	A	Runs well	124.8 tok/s	2821 ms	8K

Inference speed

Falcon 40B Instruct inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Falcon 40B Instruct at Q5_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is 2× RX 7900 XTX 24GB at ~45 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?
2× RX 7900 XTX 24GB	48 GB	Q5_K_M	45.3	Fits
2× RTX 4090 24GB	48 GB	Q5_K_M	41.3	Fits
2× RTX 3090 24GB	48 GB	Q5_K_M	35.3	Fits
4× RTX 3060 12GB	48 GB	Q5_K_M	31.1	Fits
RTX 5090 32GB	32 GB	Q5_K_M	29.4	Heavy offload
MacBook Pro M4 Max 128GB	128 GB	Q5_K_M	23.1	Fits
MacBook Pro M4 Max 64GB	64 GB	Q5_K_M	23.1	Tight
Mac Studio M3 Ultra 256GB	256 GB	Q5_K_M	21.5	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q5_K_M	17.9	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q5_K_M	16.9	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q5_K_M	12.9	Offloads
RTX 4090 24GB	24 GB	Q5_K_M	10.5	Too big
RX 7900 XTX 24GB	24 GB	Q5_K_M	9.5	Too big
MacBook Pro M3 Max 64GB	64 GB	Q5_K_M	9.2	Tight
RTX 3090 24GB	24 GB	Q5_K_M	9.0	Too big
MacBook Pro M1 Max 64GB	64 GB	Q5_K_M	8.5	Tight
RTX 4080 Super 16GB	16 GB	Q5_K_M	3.7	Too big
RTX 4070 12GB	12 GB	Q5_K_M	2.2	Too big
RTX 3060 12GB	12 GB	Q5_K_M	2.0	Too big
RTX 4060 8GB	8 GB	Q5_K_M	2.0	Too big

Estimates for single-stream decoding at Q5_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 Falcon 40B Instruct (40B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	15.6 GB	Low	B61
Q3_K_S	3	19.6 GB	Low	B61
NVFP4	4	22.4 GB	Medium	B62
Q4_K_M	4	24.4 GB	Medium	B62
Q5_K_M	5	28.8 GB	High	B63
Q6_K	6	32.8 GB	High	B64
Q8_0	8	42.8 GB	Very High	B66
F16Best for your GPU	16	82.0 GB	Maximum	B68

Get started

Copy-paste commands to run Falcon 40B Instruct on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "tiiuae/falcon-40b-instruct" \
  --hf-file "falcon-40b-instruct-Q5_K_M.gguf" \
  -c 4096 -ngl 99

Your hardware

More models your NVIDIA GH200 96GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	47 tok/s
Qwen 3.5 122B A10B	122B	S	130.3 tok/s
Mistral Small 4 119B	119B	S	141.2 tok/s
GPT-OSS 120B	117B	S	49.4 tok/s
Command A 111B	111B	S	52.2 tok/s

Frequently asked questions

Can NVIDIA GH200 96GB run Falcon 40B Instruct?

Yes, NVIDIA GH200 96GB can run Falcon 40B Instruct with a A grade (Runs well). Expected decode speed: 124.8 tok/s.

How much VRAM does Falcon 40B Instruct need?

Falcon 40B Instruct (40B parameters) requires approximately 41.4 GB of memory with Q5_K_M quantization.

What is the best quantization for Falcon 40B Instruct?

The recommended quantization for Falcon 40B Instruct is Q5_K_M, which balances quality and memory efficiency.

What speed will Falcon 40B Instruct run at on NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Falcon 40B Instruct achieves approximately 124.8 tokens per second decode speed with a time-to-first-token of 1551ms using Q5_K_M quantization.

Can NVIDIA GH200 96GB run Falcon 40B Instruct for coding?

For coding workloads, Falcon 40B Instruct on NVIDIA GH200 96GB receives a A grade with 124.8 tok/s and 8K context.

What context window can Falcon 40B Instruct use on NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Falcon 40B Instruct can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.

See all results for NVIDIA GH200 96GB See all hardware for Falcon 40B Instruct

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/falcon-40b-instruct-on-gh200-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: