willitrun·ai

Can MPT-30B-Instruct run on RTX PRO 6000 Blackwell Workstation Edition 96GB?

YES — Runs Great

A74Great
Estimated from fit model

MPT-30B-Instruct needs ~55.8 GB VRAM. RTX PRO 6000 Blackwell Workstation Edition 96GB has 96.0 GB. With Q5_K_M quantization, expect ~71 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

Q5_K_M (High quality) — 55.8 GB, 71.1 tok/s, Runs well
55.8 GB required96.0 GB available
58% VRAM used

Fit status

Runs well

Decode

71.1 tok/s

TTFT

2724 ms

Safe context

8K

Memory

55.8 GB / 96.0 GB

Memory breakdown

Weights21.6 GB
KV Cache23.4 GB
Runtime1.2 GB
Headroom9.6 GB

See how fast it feels

See how fast it feelsMPT-30B-Instruct on RTX PRO 6000 Blackwell Workstation Edition 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: 71.1 tok/s decode · 2.7s TTFT (warm) · 178 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
ChatARuns well71.1 tok/s1486 ms8K
CodingARuns well71.1 tok/s2724 ms8K
Agentic CodingATight fit71.1 tok/s3962 ms8K
ReasoningARuns well71.1 tok/s3219 ms8K
RAGATight fit71.1 tok/s4952 ms8K

Inference speed

MPT-30B-Instruct inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for MPT-30B-Instruct at Q5_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is MacBook Pro M4 Max 128GB at ~28 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 / MacMemoryQuantSpeed (tok/s)Fits?
MacBook Pro M4 Max 128GB
128 GBQ5_K_M28.4Fits
Mac Studio M3 Ultra 256GB
256 GBQ5_K_M26.3Fits
MacBook Pro M4 Max 64GB
64 GBQ5_K_M22.7Heavy offload
Mac Studio M2 Ultra 128GB
128 GBQ5_K_M21.9Fits
Mac Studio M1 Ultra 128GB
128 GBQ5_K_M20.8Fits
NVIDIARTX 5090 32GB
32 GBQ5_K_M17.9Too big
MacBook Pro M4 Pro 48GB
48 GBQ5_K_M10.5Too big
MacBook Pro M3 Max 64GB
64 GBQ5_K_M9.1Heavy offload
MacBook Pro M1 Max 64GB
64 GBQ5_K_M8.3Heavy offload
NVIDIARTX 4090 24GB
24 GBQ5_K_M6.1Too big
RX 7900 XTX 24GB
24 GBQ5_K_M5.5Too big
NVIDIARTX 3090 24GB
24 GBQ5_K_M5.2Too big
NVIDIARTX 4080 Super 16GB
16 GBQ5_K_M4.3Too big
NVIDIARTX 4070 12GB
12 GBQ5_K_M2.7Too big
NVIDIARTX 3060 12GB
12 GBQ5_K_M2.0Too big
NVIDIARTX 4060 8GB
8 GBQ5_K_M2.0Too 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 MPT-30B-Instruct (30B params) fits at each quantization level on RTX PRO 6000 Blackwell Workstation Edition 96GB (96.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
11.7 GB
LowB60
Q3_K_S
3
14.7 GB
LowB61
NVFP4
4
16.8 GB
MediumB61
Q4_K_M
4
18.3 GB
MediumB61
Q5_K_M
5
21.6 GB
HighB61
Q6_K
6
24.6 GB
HighB62
Q8_0
8
32.1 GB
Very HighB63
F16Best for your GPU
16
61.5 GB
MaximumB68

Get started

Copy-paste commands to run MPT-30B-Instruct on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \ --hf-repo "mosaicml/mpt-30b-instruct" \ --hf-file "mpt-30b-instruct-Q5_K_M.gguf" \ -c 4096 -ngl 99

Your hardware

More models your RTX PRO 6000 Blackwell Workstation Edition 96GB can run

ModelParamsGradeDecodeCapabilities
MistralDevstral 2 123B Instruct123BS21.8 tok/s
AlibabaQwen3-Coder 30B A3B Instruct30.5BS227.6 tok/s
AlibabaQwen 3.5 122B A10B122BS60.5 tok/s
AlibabaQwen 3.6 35B A3B35BS191.3 tok/s
AlibabaQwen 3.5 35B A3B35BS208 tok/s

Frequently asked questions

Can RTX PRO 6000 Blackwell Workstation Edition 96GB run MPT-30B-Instruct?

Yes, RTX PRO 6000 Blackwell Workstation Edition 96GB can run MPT-30B-Instruct with a A grade (Runs well). Expected decode speed: 71.1 tok/s.

How much VRAM does MPT-30B-Instruct need?

MPT-30B-Instruct (30B parameters) requires approximately 55.8 GB of memory with Q5_K_M quantization.

What is the best quantization for MPT-30B-Instruct?

The recommended quantization for MPT-30B-Instruct is Q5_K_M, which balances quality and memory efficiency.

What speed will MPT-30B-Instruct run at on RTX PRO 6000 Blackwell Workstation Edition 96GB?

On RTX PRO 6000 Blackwell Workstation Edition 96GB, MPT-30B-Instruct achieves approximately 71.1 tokens per second decode speed with a time-to-first-token of 2724ms using Q5_K_M quantization.

Can RTX PRO 6000 Blackwell Workstation Edition 96GB run MPT-30B-Instruct for coding?

For coding workloads, MPT-30B-Instruct on RTX PRO 6000 Blackwell Workstation Edition 96GB receives a A grade with 71.1 tok/s and 8K context.

What context window can MPT-30B-Instruct use on RTX PRO 6000 Blackwell Workstation Edition 96GB?

On RTX PRO 6000 Blackwell Workstation Edition 96GB, MPT-30B-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 RTX PRO 6000 Blackwell Workstation Edition 96GBSee all hardware for MPT-30B-Instruct
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/mpt-30b-instruct-on-rtx-pro-6000-blackwell-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: