MiniCPM-V 4.7 35B-A3B hardware requirements

What is MiniCPM-V 4.7 35B-A3B?

MiniCPM-V 4.7 35B-A3B is a vision-language model that OpenBMB released in October 2026, the first mixture-of-experts model in the MiniCPM-V series. It accepts one or more images and video, and its model card includes guides for OCR and PDF parsing. Thinking mode is on by default, and about 3B of its 35B parameters are active per token.

Model card

About the model

Parameters: 35.21B total · 3B active (MoE)
Attention: Hybrid attention (only some layers use full attention)
Max context: 262,144 tokens
Released: 2026-10-07
Model card: MiniCPM-V 4.7 35B-A3B on Hugging Face

GGUF files

Tracked quantizations of MiniCPM-V 4.7 35B-A3B, smallest first
Quant	File size	Quality	Published by
IQ4_XS	18.73 GB	Good balance	Official GGUF · openbmb
Q4_K_Mbaseline	21.17 GB	Good balance	Official GGUF · openbmb
Q8_0	36.90 GB	Near-lossless	Official GGUF · openbmb

File sizes do not include the vision projector (mmproj) that image input needs.

Memory needed by quant and context

Graphics card memory in GB: weights loaded on the GPU + f16 KV cache + compute buffer. Add about 0.6 GB if the GPU also drives your display on Windows. Part of the file stays off the graphics card: llama.cpp keeps the input embedding table in system RAM. A Mac counts the whole file, so it needs a little more.
Quant	4k	8k	16k	32k	64k	128k	256k
IQ4_XS	19.1	19.2	19.4	19.9	20.9	22.8	26.7
Q4_K_M	21.5	21.6	21.9	22.3	23.3	25.3	29.1
Q8_0	37.0	37.1	37.3	37.8	38.8	40.7	44.6

Which GPUs can run MiniCPM-V 4.7 35B-A3B?

How to read the verdicts

Runs great: Fully on the GPU at 20 tok/s or more
Runs well: Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
Runs slowly: 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
Won't run: Does not fit, or under 2 tok/s

Sort

Filter this list by budget, type and context in the calculator

Scroll sideways to see every column.

56 GPUs, Macs and CPU setups at Q4_K_M with 8k context, sorted by verdict and speed
Hardware	Verdict	Speed	Quant	Memory	Runs as	Context	Notes	Price
GeForce RTX 5090	Runs great	est. 239.5 tok/s191.6–287.4calibrated estimate ±20%	Q4_K_M	22.2 / 32.0 GB	Full GPU	up to 256k	—	$4,200 street (as of 2026-08-09)
GeForce RTX 3090 Ti	Runs great	est. 181.6 tok/s145.3–217.9calibrated estimate ±20%	Q4_K_M	22.2 / 24.0 GB	Full GPU	up to 64k	—	$1,999 launch MSRP
GeForce RTX 4090	Runs great	est. 181.6 tok/s145.3–217.9calibrated estimate ±20%	Q4_K_M	22.2 / 24.0 GB	Full GPU	up to 64k	—	$2,755 street (as of 2026-08-09)
GeForce RTX 3090	Runs great	est. 174.2 tok/s139.3–209.0calibrated estimate ±20%	Q4_K_M	22.2 / 24.0 GB	Full GPU	up to 64k	—	$1,050 street (as of 2026-08-09)
GeForce RTX 5090 Laptop	Runs great	est. 169.9 tok/s135.9–203.8calibrated estimate ±20%	Q4_K_M	22.2 / 24.0 GB	Full GPU	up to 64k	—	—
Apple M5 Ultra · 96 GB	Runs great	est. 130.8 tok/s104.7–157.0calibrated estimate ±20%	Q4_K_M	21.9 / 67.2 GB	Unified memory	up to 256k	—	—
Apple M5 Max (40-core GPU) · 48 GB	Runs great	est. 129.2 tok/s103.4–155.1calibrated estimate ±20%	Q4_K_M	21.9 / 33.6 GB	Unified memory	up to 256k	—	—
Radeon RX 7900 XTX	Runs great	est. 126.5 tok/s101.2–151.8calibrated estimate ±20%	Q4_K_M	22.2 / 24.0 GB	Full GPU	up to 64k	—	$999 launch MSRP
Apple M4 Max (40-core GPU) · 48 GB	Runs great	est. 120.3 tok/s96.3–144.4calibrated estimate ±20%	Q4_K_M	21.9 / 33.6 GB	Unified memory	up to 256k	—	—
Apple M3 Ultra · 96 GB	Runs great	est. 109.0 tok/s87.2–130.8calibrated estimate ±20%	Q4_K_M	21.9 / 67.2 GB	Unified memory	up to 256k	—	—
Apple M5 Max (32-core GPU) · 36 GB	Runs great	est. 107.8 tok/s86.2–129.3calibrated estimate ±20%	Q4_K_M	21.9 / 25.2 GB	Unified memory	up to 64k	—	—
Apple M2 Ultra · 64 GB	Runs great	est. 107.7 tok/s86.2–129.2calibrated estimate ±20%	Q4_K_M	21.9 / 44.8 GB	Unified memory	up to 256k	—	—
Apple M4 Max (32-core GPU) · 36 GB	Runs great	est. 99.7 tok/s79.8–119.7calibrated estimate ±20%	Q4_K_M	21.9 / 25.2 GB	Unified memory	up to 64k	—	—
Apple M5 Pro · 48 GB	Runs great	est. 81.0 tok/s64.8–97.3calibrated estimate ±20%	Q4_K_M	21.9 / 33.6 GB	Unified memory	up to 128k	—	—
NVIDIA DGX Spark · 64 GB	Runs great	est. 76.0 tok/s60.8–91.2calibrated estimate ±20%	Q4_K_M	21.9 / 48.2 GB	Unified memory	up to 128k	—	$3,999 launch MSRP (128 GB)
Apple M4 Pro · 48 GB	Runs great	est. 74.2 tok/s59.3–89.0calibrated estimate ±20%	Q4_K_M	21.9 / 33.6 GB	Unified memory	up to 128k	—	—
Ryzen AI Max+ 395 (Strix Halo) · 32 GB	Runs great	est. 67.5 tok/s54.0–81.1calibrated estimate ±20%	Q4_K_M	21.9 / 22.4 GB	Unified memory	up to 16k	—	$1,999 launch MSRP (128 GB)
Apple M6 · 32 GB	Runs great	est. 50.8 tok/s40.6–60.9calibrated estimate ±20%	Q4_K_M	21.9 / 22.4 GB	Unified memory	up to 16k	—	—
Apple M5 · 32 GB	Runs great	est. 46.4 tok/s37.2–55.7calibrated estimate ±20%	Q4_K_M	21.9 / 22.4 GB	Unified memory	up to 16k	—	—
Apple M4 · 32 GB	Runs great	est. 37.5 tok/s30.0–45.0calibrated estimate ±20%	Q4_K_M	21.9 / 22.4 GB	Unified memory	up to 16k	—	—
GeForce RTX 5080	Runs well	est. 99.0 tok/s69.3–128.7theoretical estimate ±30%	Q4_K_M	15.4 / 16.0 GB + 7.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$1,256 street (as of 2026-08-09)
GeForce RTX 5070 Ti	Runs well	est. 97.0 tok/s67.9–126.1theoretical estimate ±30%	Q4_K_M	15.4 / 16.0 GB + 7.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$949 street (as of 2026-08-09)
GeForce RTX 5080 Laptop	Runs well	est. 97.0 tok/s67.9–126.1theoretical estimate ±30%	Q4_K_M	15.4 / 16.0 GB + 7.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	—
Radeon RX 7900 XT	Runs well	est. 96.3 tok/s67.4–125.2theoretical estimate ±30%	Q4_K_M	19.3 / 20.0 GB + 3.2 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory Try IQ4_XS: Runs great	$899 launch MSRP
GeForce RTX 4080 Super	Runs well	est. 91.1 tok/s63.8–118.4theoretical estimate ±30%	Q4_K_M	15.4 / 16.0 GB + 7.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$999 launch MSRP
GeForce RTX 4080	Runs well	est. 90.3 tok/s63.2–117.4theoretical estimate ±30%	Q4_K_M	15.4 / 16.0 GB + 7.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$1,199 launch MSRP
GeForce RTX 4070 Ti Super	Runs well	est. 88.2 tok/s61.8–114.7theoretical estimate ±30%	Q4_K_M	15.4 / 16.0 GB + 7.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$799 launch MSRP
GeForce RTX 4090 Laptop	Runs well	est. 83.2 tok/s58.2–108.1theoretical estimate ±30%	Q4_K_M	15.4 / 16.0 GB + 7.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	—
GeForce RTX 3080 12GB	Runs well	est. 78.2 tok/s54.8–101.7theoretical estimate ±30%	Q4_K_M	11.5 / 12.0 GB + 11.0 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$799 launch MSRP
GeForce RTX 5060 Ti 16GB	Runs well	est. 74.7 tok/s52.3–97.1theoretical estimate ±30%	Q4_K_M	15.4 / 16.0 GB + 7.1 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$569 street (as of 2026-08-09)
Radeon RX 9070	Runs well	est. 73.2 tok/s51.2–95.1theoretical estimate ±30%	Q4_K_M	15.4 / 16.0 GB + 7.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$639 street (as of 2026-08-09)
Radeon RX 9070 XT	Runs well	est. 73.2 tok/s51.2–95.1theoretical estimate ±30%	Q4_K_M	15.4 / 16.0 GB + 7.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$689 street (as of 2026-08-09)
GeForce RTX 5070	Runs well	est. 72.5 tok/s50.7–94.2theoretical estimate ±30%	Q4_K_M	11.5 / 12.0 GB + 11.0 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$629 street (as of 2026-08-09)
GeForce RTX 5070 Ti Laptop	Runs well	est. 72.5 tok/s50.7–94.2theoretical estimate ±30%	Q4_K_M	11.5 / 12.0 GB + 11.0 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	—
Radeon RX 7800 XT	Runs well	est. 72.5 tok/s50.7–94.2theoretical estimate ±30%	Q4_K_M	15.4 / 16.0 GB + 7.1 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$499 launch MSRP
GeForce RTX 3080 10GB	Runs well	est. 67.1 tok/s47.0–87.2theoretical estimate ±30%	Q4_K_M	9.1 / 10.0 GB + 13.5 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$699 launch MSRP
GeForce RTX 2080 Ti	Runs well	est. 66.4 tok/s46.5–86.3theoretical estimate ±30%	Q4_K_M	10.0 / 11.0 GB + 12.5 GB RAM	MoE experts in RAM	up to 256k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$999 launch MSRP
GeForce RTX 4070	Runs well	est. 66.3 tok/s46.4–86.2theoretical estimate ±30%	Q4_K_M	11.5 / 12.0 GB + 11.0 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$599 launch MSRP
GeForce RTX 4070 Super	Runs well	est. 66.3 tok/s46.4–86.2theoretical estimate ±30%	Q4_K_M	11.5 / 12.0 GB + 11.0 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$599 launch MSRP
GeForce RTX 4080 Laptop	Runs well	est. 62.7 tok/s43.9–81.6theoretical estimate ±30%	Q4_K_M	11.5 / 12.0 GB + 11.0 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	—
GeForce GTX 1080 Ti	Runs well	est. 61.8 tok/s43.3–80.4theoretical estimate ±30%	Q4_K_M	10.0 / 11.0 GB + 12.5 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$699 launch MSRP
GeForce RTX 4060 Ti 16GB	Runs well	est. 59.5 tok/s41.6–77.3theoretical estimate ±30%	Q4_K_M	15.4 / 16.0 GB + 7.1 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$499 launch MSRP
GeForce RTX 3060 12GB	Runs well	est. 58.4 tok/s40.9–75.9theoretical estimate ±30%	Q4_K_M	11.5 / 12.0 GB + 11.0 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$250 street (as of 2026-08-09)
Radeon RX 9060 XT 16GB	Runs well	est. 56.7 tok/s39.7–73.8theoretical estimate ±30%	Q4_K_M	15.4 / 16.0 GB + 7.1 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$449 street (as of 2026-08-09)
GeForce RTX 3070	Runs well	est. 54.5 tok/s38.2–70.9theoretical estimate ±30%	Q4_K_M	7.1 / 8.0 GB + 15.4 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$499 launch MSRP
GeForce RTX 5060	Runs well	est. 54.5 tok/s38.2–70.9theoretical estimate ±30%	Q4_K_M	7.1 / 8.0 GB + 15.4 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$339 street (as of 2026-08-09)
GeForce RTX 5060 Ti 8GB	Runs well	est. 54.5 tok/s38.2–70.9theoretical estimate ±30%	Q4_K_M	7.1 / 8.0 GB + 15.4 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$429 street (as of 2026-08-09)
Intel Arc B580	Runs well	est. 52.1 tok/s36.5–67.8theoretical estimate ±30%	Q4_K_M	11.5 / 12.0 GB + 11.0 GB RAM	MoE experts in RAM	up to 128k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$290 street (as of 2026-08-09)
GeForce RTX 4060 Ti 8GB	Runs well	est. 46.9 tok/s32.8–61.0theoretical estimate ±30%	Q4_K_M	7.1 / 8.0 GB + 15.4 GB RAM	MoE experts in RAM	up to 64k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$399 launch MSRP
GeForce RTX 4060	Runs well	est. 45.9 tok/s32.1–59.6theoretical estimate ±30%	Q4_K_M	7.1 / 8.0 GB + 15.4 GB RAM	MoE experts in RAM	up to 64k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$299 launch MSRP
GeForce RTX 4060 Laptop	Runs well	est. 44.7 tok/s31.3–58.2theoretical estimate ±30%	Q4_K_M	7.1 / 8.0 GB + 15.4 GB RAM	MoE experts in RAM	up to 64k	Not fully on the GPU — Runs great needs the whole model in GPU memory	—
GeForce RTX 4070 Laptop	Runs well	est. 44.7 tok/s31.3–58.2theoretical estimate ±30%	Q4_K_M	7.1 / 8.0 GB + 15.4 GB RAM	MoE experts in RAM	up to 64k	Not fully on the GPU — Runs great needs the whole model in GPU memory	—
GeForce RTX 3050 8GB	Runs well	est. 42.2 tok/s29.6–54.9theoretical estimate ±30%	Q4_K_M	7.1 / 8.0 GB + 15.4 GB RAM	MoE experts in RAM	up to 64k	Not fully on the GPU — Runs great needs the whole model in GPU memory	$249 launch MSRP
DDR5-6000 dual-channel CPU · 32 GB	Runs slowly	est. 20.9 tok/s16.8–25.1calibrated estimate ±20%	Q4_K_M	21.3 GB RAM	CPU only	up to 256k	CPU inference — capped at Runs slowly	—
DDR5-5600 dual-channel CPU · 32 GB	Runs slowly	est. 19.5 tok/s15.6–23.5calibrated estimate ±20%	Q4_K_M	21.3 GB RAM	CPU only	up to 256k	CPU inference — capped at Runs slowly	—
DDR4-3200 dual-channel CPU · 32 GB	Runs slowly	est. 11.2 tok/s8.9–13.4calibrated estimate ±20%	Q4_K_M	21.3 GB RAM	CPU only	up to 256k	—	—

Models with a thinking mode spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s). With thinking turned off, a model may do one grade better.

Cheapest GPUs that run it

Runs greatGeForce RTX 3090$1,050 street (as of 2026-08-09), est. 174.2 tok/s (139.3–209.0, calibrated estimate ±20%).
Runs wellGeForce RTX 3060 12GB$250 street (as of 2026-08-09), est. 58.4 tok/s (40.9–75.9, theoretical estimate ±30%).

Measured results for MiniCPM-V 4.7 35B-A3B

No public measurements for this model yet.

Frequently asked questions

How much VRAM does MiniCPM-V 4.7 35B-A3B need?

At Q4_K_M the file is 21.17 GB; with 8k context a graphics card needs about 21.6 GB (weights 20.87 GB, KV cache 0.2 GB, compute buffer 0.6 GB). The smallest tracked file (IQ4_XS) needs about 19.2 GB. Part of the file stays off the graphics card: llama.cpp keeps the input embedding table in system RAM. A Mac counts the whole file, so it needs a little more.

What is the cheapest GPU that runs MiniCPM-V 4.7 35B-A3B well?

Cheapest that runs it great: GeForce RTX 3090 at $1,050 (street price as of 2026-08-09), est. 174.2 tok/s (139.3–209.0, calibrated estimate ±20%). Cheaper and still Runs well: GeForce RTX 3060 12GB at $250 (street price as of 2026-08-09), est. 58.4 tok/s (40.9–75.9, theoretical estimate ±30%).

Can MiniCPM-V 4.7 35B-A3B run on an 8 GB, 16 GB or 24 GB GPU?

At Q4_K_M with 8k context: GeForce RTX 4060 — Runs well, est. 45.9 tok/s (32.1–59.6, theoretical estimate ±30%); GeForce RTX 5060 Ti 16GB — Runs well, est. 74.7 tok/s (52.3–97.1, theoretical estimate ±30%); GeForce RTX 3090 — Runs great, est. 174.2 tok/s (139.3–209.0, calibrated estimate ±20%).

Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.