MPT-30B-Instruct needs ~59.3 GB VRAM. NVIDIA DGX Spark 128GB has 108.8 GB. With Q5_K_M quantization, expect ~8 tok/s.
Operating mode
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.
Select quantization to explore
Fit status
Runs well
Decode
7.7 tok/s
TTFT
25029 ms
Safe context
8K
Memory
59.3 GB / 108.8 GB
The model fits in shared memory, but shared-memory bandwidth is now the real limiter.
Fit does not mean dedicated-VRAM speed
Unified or shared memory can make a model technically fit, but sustained tokens per second may still trail a discrete high-bandwidth GPU with less total memory.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
Prioritize bandwidth, not only capacity
If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 7.7 tok/s | 13652 ms | 8K |
| Coding | B | Runs well | 7.7 tok/s | 25029 ms | 8K |
| Agentic Coding | B | Runs well | 7.7 tok/s | 36406 ms | 8K |
| Reasoning | B | Runs well | 7.7 tok/s | 29580 ms | 8K |
| RAG | B | Runs well | 7.7 tok/s | 45507 ms | 8K |
Inference speed
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 / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
MacBook Pro M4 Max 128GB | 128 GB | Q5_K_M | 28.4 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q5_K_M | 26.3 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q5_K_M | 22.7 | Heavy offload |
Mac Studio M2 Ultra 128GB | 128 GB | Q5_K_M | 21.9 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q5_K_M | 20.8 | Fits |
 RTX 5090 32GB | 32 GB | Q5_K_M | 17.9 | Too big |
MacBook Pro M4 Pro 48GB | 48 GB | Q5_K_M | 10.5 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q5_K_M | 9.1 | Heavy offload |
MacBook Pro M1 Max 64GB | 64 GB | Q5_K_M | 8.3 | Heavy offload |
| RTX 4090 24GB | 24 GB | Q5_K_M | 6.1 | Too big |
RX 7900 XTX 24GB | 24 GB | Q5_K_M | 5.5 | Too big |
| RTX 3090 24GB | 24 GB | Q5_K_M | 5.2 | Too big |
| RTX 4080 Super 16GB | 16 GB | Q5_K_M | 4.3 | Too big |
| RTX 4070 12GB | 12 GB | Q5_K_M | 2.7 | 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.
How MPT-30B-Instruct (30B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 11.7 GB | Low | B60 |
Q3_K_S | 3 | 14.7 GB | Low | B61 |
NVFP4 | 4 | 16.8 GB | Medium | B61 |
Q4_K_M | 4 | 18.3 GB | Medium | B61 |
Q5_K_M | 5 | 21.6 GB | High | B62 |
Q6_K | 6 | 24.6 GB | High | B62 |
Q8_0 | 8 | 32.1 GB | Very High | B64 |
F16Best for your GPU | 16 | 61.5 GB | Maximum | B68 |
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 99Upgrade options
NVIDIA H200 141GBBudget pickRaises estimated decode speed by about 2373%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
NVIDIA H200 PCIe 141GBBest valueRaises estimated decode speed by about 2373%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
NVIDIA B200 180GBNVIDIA upgradeRaises estimated decode speed by about 4021%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Yes, NVIDIA DGX Spark 128GB can run MPT-30B-Instruct with a B grade (Runs well). Expected decode speed: 7.7 tok/s.
MPT-30B-Instruct (30B parameters) requires approximately 59.3 GB of memory with Q5_K_M quantization.
The recommended quantization for MPT-30B-Instruct is Q5_K_M, which balances quality and memory efficiency.
On NVIDIA DGX Spark 128GB, MPT-30B-Instruct achieves approximately 7.7 tokens per second decode speed with a time-to-first-token of 25029ms using Q5_K_M quantization.
For coding workloads, MPT-30B-Instruct on NVIDIA DGX Spark 128GB receives a B grade with 7.7 tok/s and 8K context.
On NVIDIA DGX Spark 128GB, 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.
Prioritize bandwidth, not only capacity. If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
Not always. NVIDIA DGX Spark 128GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/mpt-30b-instruct-on-dgx-spark-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: