llamaperf

Minimax M2.1

5 reports

Minimax M2.1 230B · 10B active at 4-bit generates a median of 25.0 tokens per second on the M3 Ultra 256GB, the hardware it is most run on, from one plain run (community reports, as of 22 Nov 2026).

As of 22 Nov 2026, Minimax M2.1 230B · 10B active at 4-bit on each device, fastest first, with the median generation speed of plain runs (one device, one request, no speculative decoding, the whole model in its memory):

Bars are medians on one scale, 0 to 25.0 tokens/s. Press ▶ to watch text arrive at a row's speed.

Minimax M2.1 VRAM requirements by size and quant →

How does Minimax M2.1 run on your hardware?

Pick your GPU or Mac, then read the speeds people reported for Minimax M2.1 on it, or estimate memory fit and speed.

Free to use. No account needed. Memory estimates and community measurements are labelled separately.

Run Minimax M2.1 yourself? Add your numbers.

Your coding agent can run a speed test on your machine and send it here with a free account. Or paste a result you've already posted.

Reported performance for Minimax M2.1

Filter this model’s reports by setup →

Speeds are as each source reported them. GPU count, offloading and concurrent requests change them, and prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing two reports.

Minimax M2.1 IQ4_XS / ROCm b7822 / native PP256 and separate TG256

AMD Radeon Graphics gfx1151 (marketing SKU and installed RAM unreported) · llama.cpp b7822 / 8f91ca54e / ROCm 7.1.1

generation:
28.9 tokens/s
prompt processing (prefill):
147.6 tokens/s
quant:
IQ4_XS (GGUF)
flash attention:
on

User reports Minimax M2.1 at 28.9 t/s generation and 147.6 t/s prompt processing on an AMD Radeon Graphics gfx1151 device. Setup is llama-bench on ROCm 7.1.1 with IQ4_XS, ngl=999, FA=1, and dev=ROCm0, selecting one GPU. The native figures are PP256 147.63 +/- 2.44 and TG256 28.92 +/- 0.21; exact context depth, CPU threads, and repetitions are unknown.

Oct 14, 2026

Minimax M2.1 IQ4_XS / ROCm b7819 / native PP4096 and separate TG512

AMD Radeon 8060S integrated GPU (Strix Halo; installed RAM unreported) · llama.cpp b7819 / 557515be1 / ROCm 6.4.4

generation:
28.3 tokens/s
prompt processing (prefill):
248.5 tokens/s
quant:
IQ4_XS (GGUF)
flash attention:
on

User reports Minimax M2.1 at 28.3 t/s generation and 248.5 t/s prompt processing on a single Radeon 8060S Graphics (gfx1151) via ROCm. Setup is llama-bench with IQ4_XS at 4.25 bpw, -ngl 999, -fa 1, -p 4096 and -n 512, one repetition. Native figures were PP4096 248.52 and TG512 28.28 t/s, both with zero deviation; the model is 113.52 GiB and 228.69 B parameters.

Oct 14, 2026
AMD hardware
generation:
31.1 tokens/s
prompt processing (prefill):
104.8 tokens/s
quant:
UD-Q3_K_XL (GGUF)
flash attention:
on

User reports Minimax M2.1 at 31.1 t/s generation and 104.8 t/s prompt processing on an AMD Strix Halo 128GB machine. Setup is llama-bench on Vulkan0 with the UD-Q3_K_XL quant, -ngl 999, -p 256 -n 256, -t 16, -r 3 and -fa 1. The native figures are PP256 104.80 +/- 7.95 and TG256 31.13 +/- 0.02; a separate toolbox run gave PP256 104.50 +/- 8.57 and TG256 33.07 +/- 0.05.

Oct 14, 2026

Minimax M2.1 230B (10B active)

2× RTX 4090D 48GB · llama.cpp · 65,536 ctx

Tone: positive
generation:
20.1 tokens/s
prompt processing (prefill):
67.1 tokens/s
quant:
UD-Q4_K_XL (GGUF)

User reports Minimax M2.1 at 20.05 t/s generation and 67.11 t/s prompt eval on an RTX 4090D 48GB plus an RTX 3090. Setup is llama.cpp build 7542 with UD-Q4_K_XL GGUF at 65536 context, running in router mode on a Xeon W5-3425 with 256GB DDR5. User notes speed is lower at larger context and says it works great.

Oct 9, 2026
Tone: negativeApple hardware
generation:
25.0 tokens/s
quant:
4bit
agenticcodinglong-context

User reports Minimax-m2.1-4bit at 25 t/s generation on an M3 Ultra 256GB with 80-core GPU, compared against llama.cpp with flash attention at 32 t/s. Setup is MLX with 4bit weights at 30K context; the same model under llama.cpp with flash attention reached 32 t/s generation and 78s prompt processing. At 146K context MLX fell to 5.95 t/s generation versus 12.12 t/s for llama.cpp, and the user says MLX runs about 50% slower on long-context generation, impacting agentic coding.

Oct 4, 2026
Engines people run Minimax M2.1 with
EngineReports
MLX1
llama.cpp1

Get a weekly email of new Minimax M2.1 reports on any GPU.

Email me new reports

Reported configurations

Individual observations from this page, not expected speeds or a ranking. Select a model to open its report, with the source and offloading conditions. Reported context may be a limit rather than actual input length.

Model / hardwareQuant / engineReported contextGeneration
Minimax M2.1 UD-Q3_K_XL / original Vulkan / native PP256 and separate TG256
AMD Strix Halo 128GB
UD-Q3_K_XL
llama.cpp / Vulkan RADV (original build unreported)
Not reported31.1 tokens/s
Minimax M2.1 230B (10B active)
M3 Ultra 256GB
4bit
MLX
30,00025.0 tokens/s

Frequently asked

What hardware do people run Minimax M2.1 on?

The hardware Minimax M2.1 230B · 10B active at 4-bit is most run on: M3 Ultra 256GB (25.0 t/s median, one run). Medians of plain runs, as of 22 Nov 2026.

Which inference engines do people use for Minimax M2.1?

Reports of Minimax M2.1 name MLX (1 report), llama.cpp (1 report), as of 22 Nov 2026.