DeepSeek-V4.1-Flash-1017-Sushi-STQ

DeepSeek-V4.1-Flash family · 552.0B params

2recorded runs

144.8best tok/s

2verified

Evidence: 2 sourced runs · 1 independent source · first recorded Oct 30, 2026. What these labels mean.

What the DeepSeek-V4.1-Flash-1017-Sushi-STQ numbers mean

The fastest verified result on our board is 144.8 output tok/s on an Apple M5 Max 128GB at 4bpw with a 4096-token context. That is about 6.9 ms per generated token — 500 tokens takes roughly 3.5 seconds.

How much VRAM does DeepSeek-V4.1-Flash-1017-Sushi-STQ need?

DeepSeek-V4.1-Flash-1017-Sushi-STQ has 552.0B parameters. These estimates use the same formula as the VRAM calculator: weights, plus about 15% for a moderate-context KV cache and runtime overhead, plus a small engine floor.

Quantisation	Estimated VRAM	Smallest card that fits
Q4_K_M (4-bit)	357.9 GB	multi-GPU or CPU offload
Q8_0 (8-bit)	675.3 GB	multi-GPU or CPU offload
FP16 (16-bit)	1270.4 GB	multi-GPU or CPU offload

Long contexts and large batches raise the real number — read the smallest card as "possible with a reduced context". Measured throughput is on the benchmark board.

Fastest GPUs for this model (best tok/s)

Apple M5 Max 128GB144.8

Models with a similar footprint

Model	Params	Q4_K_M weights
DeepSeek-V4.1-Flash	552B	310.5 GB
DeepSeek-V4.1-Flash-1017	552B	310.5 GB
Beam-1.0	501B	281.8 GB
MiniMax M3.1 Flash	428B	240.8 GB
GLM-5.2	753B	423.6 GB
GLM-5.3-Flash	321B	180.6 GB

Ranked by distance from DeepSeek-V4.1-Flash-1017-Sushi-STQ's parameter count. Full benchmark board.

All benchmarks Methodology

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
Apple M5 Max 128GB · 128 GB	DeepSeek-V4.1-Flash-1017-Sushi-STQ	4bpw	sushi v1.4.1	4096	144.8 ✓	—	—	src
Apple M5 Max 128GB · 128 GB	DeepSeek-V4.1-Flash-1017-Sushi-STQ	2.4bpw	sushi v1.4.1	4096	70.5 ✓	—	—	src