Moore Threads MTT S4000
VRAM
48 GB
Memory
GDDR6
Bandwidth
768 GB/s
FP16
100 TF
TDP
-
Memory and compute
Architecture and power
Notes
China market. Vendor-published specs: 100 TFLOPS FP16/BF16, 200 TOPS INT8, 48GB GDDR6 at 768 GB/s, MTLink multi-card interconnect. Used domestically for LLM training clusters.
Models that may fit on Moore Threads MTT S4000
Estimates based on INT8 quantization. Actual fit depends on framework and batch size.
Frequently asked questions about Moore Threads MTT S4000
Answered from the entry's own figures: memory, which models fit, bandwidth, power and the card's class.
Moore Threads MTT S4000 has 48 GB of GDDR6 at 768 GB/s. At INT8 a model's weights take about one byte per parameter, so the card holds roughly a 38B-parameter model with room for context; larger models need several cards or a lower precision.
From the catalog's estimates at INT8, Gemma 4 31B IT, Qwen 2.5 32B Instruct, DeepSeek R1 Distill Qwen 32B and Aya Vision 32B fit on a single Moore Threads MTT S4000 with their default context. The list on this page shows the estimated memory each takes; the capacity planner sizes any model against this card for your own context length, batch size and request rate.
768 GB/s. Bandwidth bounds how fast a model generates tokens, because every token reads the whole set of weights and the KV cache from memory; at this rate a 38B model at INT8 could be read on the order of 20 times a second on one card, before batching and framework efficiency.
Moore Threads has not published a TDP for Moore Threads MTT S4000; the card ships in the PCIe form factor. The catalog shows the figure as not published rather than estimating it.
Moore Threads MTT S4000 is a datacenter accelerator, meant for servers and multi-GPU serving, built on the MUSA 3 architecture and released in 2023. It supports a multi-GPU interconnect, so a model larger than one card can be split across several.
Specifications from the manufacturer's published material; a figure that is not published is shown as such, and a derived one is explained in the notes.
Added Jul 30, 2026 · Last updated Jul 30, 2026
Explore more
Companion tools that draw on the same catalog and routing engine.
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.