MiniCPM5 2B hardware requirements
What is MiniCPM5 2B?
MiniCPM5 2B is a compact dense model that OpenBMB released in September 2026 for on-device and local use. Its model card names coding, math, long-context understanding and tool use as strengths. OpenBMB also publishes official GGUF files for llama.cpp, Ollama and LM Studio.
About the model
- Parameters
- 2.52B
- Attention
- Full attention
- Max context
- 131,072 tokens
- Released
- 2026-09-06
- Model card
- MiniCPM5 2B on Hugging Face
Other sizes in this series
| Model | Parameters | Baseline quant | Memory needed (8k) | GeForce RTX 4060 | GeForce RTX 5060 Ti 16GB | GeForce RTX 3090 |
|---|---|---|---|---|---|---|
| MiniCPM5 1B | 1.08B | Q4_K_M | 1.3 GB | Runs great | Runs great | Runs great |
| MiniCPM5 2Bthis model | 2.52B | Q4_K_M | 2.3 GB | Runs great | Runs great | Runs great |
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| Q4_K_Mbaseline | 1.56 GB | Good balance | Official GGUF · openbmb |
| Q8_0 | 2.68 GB | Near-lossless | Official GGUF · openbmb |
Memory needed by quant and context
| Quant | 4k | 8k | 16k | 32k | 64k | 128k |
|---|---|---|---|---|---|---|
| Q4_K_M | 2.1 | 2.3 | 2.8 | 3.6 | 5.3 | 8.7 |
| Q8_0 | 3.1 | 3.3 | 3.7 | 4.6 | 6.3 | 9.7 |
Which GPUs can run MiniCPM5 2B?
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
Filter this list by budget, type and context in the calculator
Scroll sideways to see every column.
| Hardware | Verdict | Speed | Quant | Memory | Runs as | Context | Notes | Price |
|---|---|---|---|---|---|---|---|---|
| GeForce RTX 5090 | Runs great | est. 656.0 tok/s577.2–734.7calibrated estimate ±12% | Q4_K_M | 2.9 / 32.0 GB | Full GPU | up to 128k | — | $4,200 street (as of 2026-08-09) |
| NVIDIA RTX PRO 6000 Blackwell | Runs great | est. 656.0 tok/s577.2–734.7calibrated estimate ±12% | Q4_K_M | 2.9 / 96.0 GB | Full GPU | up to 128k | — | — |
| NVIDIA RTX PRO 6000 Blackwell Max-Q | Runs great | est. 656.0 tok/s577.2–734.7calibrated estimate ±12% | Q4_K_M | 2.9 / 96.0 GB | Full GPU | up to 128k | — | — |
| Radeon RX 7900 XTX | Runs great | est. 381.5 tok/s335.7–427.3calibrated estimate ±12% | Q4_K_M | 2.9 / 24.0 GB | Full GPU | up to 128k | — | $999 launch MSRP |
| GeForce RTX 3090 Ti | Runs great | est. 369.0 tok/s324.7–413.3calibrated estimate ±12% | Q4_K_M | 2.9 / 24.0 GB | Full GPU | up to 128k | — | $1,999 launch MSRP |
| GeForce RTX 4090 | Runs great | est. 369.0 tok/s324.7–413.3calibrated estimate ±12% | Q4_K_M | 2.9 / 24.0 GB | Full GPU | up to 128k | — | $2,755 street (as of 2026-08-09) |
| Apple M5 Ultra · 96 GB | Runs great | est. 366.0 tok/s292.8–439.2calibrated estimate ±20% | Q4_K_M | 2.5 / 67.2 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 5080 | Runs great | est. 351.4 tok/s309.2–393.6calibrated estimate ±12% | Q4_K_M | 2.9 / 16.0 GB | Full GPU | up to 128k | — | $1,256 street (as of 2026-08-09) |
| GeForce RTX 3090 | Runs great | est. 342.6 tok/s301.5–383.7calibrated estimate ±12% | Q4_K_M | 2.9 / 24.0 GB | Full GPU | up to 128k | — | $1,050 street (as of 2026-08-09) |
| GeForce RTX 3080 12GB | Runs great | est. 333.8 tok/s293.8–373.9calibrated estimate ±12% | Q4_K_M | 2.9 / 12.0 GB | Full GPU | up to 128k | — | $799 launch MSRP |
| GeForce RTX 5070 Ti | Runs great | est. 328.0 tok/s288.6–367.3calibrated estimate ±12% | Q4_K_M | 2.9 / 16.0 GB | Full GPU | up to 128k | — | $949 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Runs great | est. 328.0 tok/s288.6–367.3calibrated estimate ±12% | Q4_K_M | 2.9 / 16.0 GB | Full GPU | up to 128k | — | — |
| GeForce RTX 5090 Laptop | Runs great | est. 328.0 tok/s288.6–367.3calibrated estimate ±12% | Q4_K_M | 2.9 / 24.0 GB | Full GPU | up to 128k | — | — |
| Radeon RX 7900 XT | Runs great | est. 317.9 tok/s279.8–356.1calibrated estimate ±12% | Q4_K_M | 2.9 / 20.0 GB | Full GPU | up to 128k | — | $899 launch MSRP |
| GeForce RTX 3080 10GB | Runs great | est. 278.2 tok/s244.8–311.6calibrated estimate ±12% | Q4_K_M | 2.9 / 10.0 GB | Full GPU | up to 128k | — | $699 launch MSRP |
| GeForce RTX 4080 Super | Runs great | est. 269.4 tok/s237.1–301.7calibrated estimate ±12% | Q4_K_M | 2.9 / 16.0 GB | Full GPU | up to 128k | — | $999 launch MSRP |
| GeForce RTX 4080 | Runs great | est. 262.5 tok/s231.0–294.0calibrated estimate ±12% | Q4_K_M | 2.9 / 16.0 GB | Full GPU | up to 128k | — | $1,199 launch MSRP |
| Radeon RX 9070 | Runs great | est. 256.3 tok/s225.6–287.1calibrated estimate ±12% | Q4_K_M | 2.9 / 16.0 GB | Full GPU | up to 128k | — | $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Runs great | est. 256.3 tok/s225.6–287.1calibrated estimate ±12% | Q4_K_M | 2.9 / 16.0 GB | Full GPU | up to 128k | — | $689 street (as of 2026-08-09) |
| Radeon RX 7800 XT | Runs great | est. 248.0 tok/s218.2–277.8calibrated estimate ±12% | Q4_K_M | 2.9 / 16.0 GB | Full GPU | up to 128k | — | $499 launch MSRP |
| GeForce RTX 4070 Ti Super | Runs great | est. 246.0 tok/s216.5–275.5calibrated estimate ±12% | Q4_K_M | 2.9 / 16.0 GB | Full GPU | up to 128k | — | $799 launch MSRP |
| GeForce RTX 5070 | Runs great | est. 246.0 tok/s216.5–275.5calibrated estimate ±12% | Q4_K_M | 2.9 / 12.0 GB | Full GPU | up to 128k | — | $629 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Runs great | est. 246.0 tok/s216.5–275.5calibrated estimate ±12% | Q4_K_M | 2.9 / 12.0 GB | Full GPU | up to 128k | — | — |
| Apple M3 Ultra · 96 GB | Runs great | est. 244.1 tok/s195.3–292.9calibrated estimate ±20% | Q4_K_M | 2.5 / 67.2 GB | Unified memory | up to 128k | — | — |
| Apple M5 Max (40-core GPU) · 48 GB | Runs great | est. 244.0 tok/s195.2–292.8calibrated estimate ±20% | Q4_K_M | 2.5 / 33.6 GB | Unified memory | up to 128k | — | — |
| Apple M2 Ultra · 64 GB | Runs great | est. 238.5 tok/s190.8–286.1calibrated estimate ±20% | Q4_K_M | 2.5 / 44.8 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 2080 Ti | Runs great | est. 225.5 tok/s198.4–252.5calibrated estimate ±12% | Q4_K_M | 2.9 / 11.0 GB | Full GPU | up to 128k | — | $999 launch MSRP |
| Apple M4 Max (40-core GPU) · 48 GB | Runs great | est. 217.0 tok/s173.6–260.4calibrated estimate ±20% | Q4_K_M | 2.5 / 33.6 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 4090 Laptop | Runs great | est. 210.8 tok/s185.5–236.1calibrated estimate ±12% | Q4_K_M | 2.9 / 16.0 GB | Full GPU | up to 128k | — | — |
| GeForce RTX 4070 | Runs great | est. 184.5 tok/s162.3–206.6calibrated estimate ±12% | Q4_K_M | 2.9 / 12.0 GB | Full GPU | up to 128k | — | $599 launch MSRP |
| GeForce RTX 4070 Super | Runs great | est. 184.5 tok/s162.3–206.6calibrated estimate ±12% | Q4_K_M | 2.9 / 12.0 GB | Full GPU | up to 128k | — | $599 launch MSRP |
| Apple M5 Max (32-core GPU) · 36 GB | Runs great | est. 182.8 tok/s146.3–219.4calibrated estimate ±20% | Q4_K_M | 2.5 / 25.2 GB | Unified memory | up to 128k | — | — |
| GeForce GTX 1080 Ti | Runs great | est. 177.2 tok/s124.0–230.3theoretical estimate ±30% | Q4_K_M | 2.9 / 11.0 GB | Full GPU | up to 128k | — | $699 launch MSRP |
| GeForce RTX 3070 | Runs great | est. 164.0 tok/s144.3–183.7calibrated estimate ±12% | Q4_K_M | 2.9 / 8.0 GB | Full GPU | up to 64k | — | $499 launch MSRP |
| GeForce RTX 5060 | Runs great | est. 164.0 tok/s144.3–183.7calibrated estimate ±12% | Q4_K_M | 2.9 / 8.0 GB | Full GPU | up to 64k | — | $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 16GB | Runs great | est. 164.0 tok/s144.3–183.7calibrated estimate ±12% | Q4_K_M | 2.9 / 16.0 GB | Full GPU | up to 128k | — | $569 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 8GB | Runs great | est. 164.0 tok/s144.3–183.7calibrated estimate ±12% | Q4_K_M | 2.9 / 8.0 GB | Full GPU | up to 64k | — | $429 street (as of 2026-08-09) |
| Apple M4 Max (32-core GPU) · 36 GB | Runs great | est. 162.9 tok/s130.4–195.5calibrated estimate ±20% | Q4_K_M | 2.5 / 25.2 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 4080 Laptop | Runs great | est. 158.1 tok/s139.2–177.1calibrated estimate ±12% | Q4_K_M | 2.9 / 12.0 GB | Full GPU | up to 128k | — | — |
| Intel Arc B580 | Runs great | est. 140.7 tok/s112.6–168.8calibrated estimate ±20% | Q4_K_M | 2.9 / 12.0 GB | Full GPU | up to 128k | — | $290 street (as of 2026-08-09) |
| GeForce RTX 3060 12GB | Runs great | est. 131.8 tok/s116.0–147.6calibrated estimate ±12% | Q4_K_M | 2.9 / 12.0 GB | Full GPU | up to 128k | — | $250 street (as of 2026-08-09) |
| Radeon RX 9060 XT 16GB | Runs great | est. 128.0 tok/s112.6–143.3calibrated estimate ±12% | Q4_K_M | 2.9 / 16.0 GB | Full GPU | up to 128k | — | $449 street (as of 2026-08-09) |
| Apple M5 Pro · 24 GB | Runs great | est. 122.0 tok/s97.6–146.4calibrated estimate ±20% | Q4_K_M | 2.5 / 16.8 GB | Unified memory | up to 128k | — | — |
| NVIDIA DGX Spark · 128 GB | Runs great | est. 111.4 tok/s89.1–133.6calibrated estimate ±20% | Q4_K_M | 2.5 / 116.9 GB | Unified memory | up to 64k | — | $3,999 launch MSRP (128 GB) |
| Ryzen AI Max+ 395 (Strix Halo) · 32 GB | Runs great | est. 109.8 tok/s87.8–131.7calibrated estimate ±20% | Q4_K_M | 2.5 / 22.4 GB | Unified memory | up to 64k | — | $1,999 launch MSRP (128 GB) |
| Apple M4 Pro · 24 GB | Runs great | est. 108.5 tok/s86.8–130.2calibrated estimate ±20% | Q4_K_M | 2.5 / 16.8 GB | Unified memory | up to 64k | — | — |
| GeForce RTX 4060 Ti 16GB | Runs great | est. 105.4 tok/s92.8–118.1calibrated estimate ±12% | Q4_K_M | 2.9 / 16.0 GB | Full GPU | up to 64k | — | $499 launch MSRP |
| GeForce RTX 4060 Ti 8GB | Runs great | est. 105.4 tok/s92.8–118.1calibrated estimate ±12% | Q4_K_M | 2.9 / 8.0 GB | Full GPU | up to 64k | — | $399 launch MSRP |
| GeForce RTX 4060 | Runs great | est. 99.6 tok/s87.6–111.5calibrated estimate ±12% | Q4_K_M | 2.9 / 8.0 GB | Full GPU | up to 64k | — | $299 launch MSRP |
| GeForce RTX 4060 Laptop | Runs great | est. 93.7 tok/s82.5–105.0calibrated estimate ±12% | Q4_K_M | 2.9 / 8.0 GB | Full GPU | up to 64k | — | — |
| GeForce RTX 4070 Laptop | Runs great | est. 93.7 tok/s82.5–105.0calibrated estimate ±12% | Q4_K_M | 2.9 / 8.0 GB | Full GPU | up to 64k | — | — |
| GeForce RTX 3050 8GB | Runs great | est. 82.0 tok/s72.2–91.8calibrated estimate ±12% | Q4_K_M | 2.9 / 8.0 GB | Full GPU | up to 64k | — | $249 launch MSRP |
| Apple M5 · 16 GB | Runs great | est. 61.0 tok/s48.8–73.3calibrated estimate ±20% | Q4_K_M | 2.5 / 11.2 GB | Unified memory | up to 32k | — | — |
| Apple M6 · 16 GB | Runs great | est. 61.0 tok/s48.8–73.3calibrated estimate ±20% | Q4_K_M | 2.5 / 11.2 GB | Unified memory | up to 32k | — | — |
| Apple M4 · 16 GB | Runs great | est. 47.7 tok/s38.2–57.2calibrated estimate ±20% | Q4_K_M | 2.5 / 11.2 GB | Unified memory | up to 32k | — | — |
| DDR5-6000 dual-channel CPU · 16 GB | Runs slowly | est. 25.1 tok/s20.1–30.1calibrated estimate ±20% | Q4_K_M | 1.9 GB RAM | CPU only | up to 128k |
| — |
| DDR5-5600 dual-channel CPU · 16 GB | Runs slowly | est. 23.4 tok/s18.7–28.1calibrated estimate ±20% | Q4_K_M | 1.9 GB RAM | CPU only | up to 128k |
| — |
| DDR4-3200 dual-channel CPU · 16 GB | Runs slowly | est. 13.4 tok/s10.7–16.1calibrated estimate ±20% | Q4_K_M | 1.9 GB RAM | CPU only | up to 128k |
| — |
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 3060 12GB$250 street (as of 2026-08-09), est. 131.8 tok/s (116.0–147.6, calibrated estimate ±12%).
Measured results for MiniCPM5 2B
No public measurements for this model yet.
Frequently asked questions
How much VRAM does MiniCPM5 2B need?
At Q4_K_M the file is 1.56 GB; with 8k context a graphics card needs about 2.3 GB (weights 1.40 GB, KV cache 0.4 GB, compute buffer 0.6 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 MiniCPM5 2B well?
Cheapest that runs it great: GeForce RTX 3060 12GB at $250 (street price as of 2026-08-09), est. 131.8 tok/s (116.0–147.6, calibrated estimate ±12%).
Can MiniCPM5 2B run on an 8 GB, 16 GB or 24 GB GPU?
At Q4_K_M with 8k context: GeForce RTX 4060 — Runs great, est. 99.6 tok/s (87.6–111.5, calibrated estimate ±12%); GeForce RTX 5060 Ti 16GB — Runs great, est. 164.0 tok/s (144.3–183.7, calibrated estimate ±12%); GeForce RTX 3090 — Runs great, est. 342.6 tok/s (301.5–383.7, calibrated estimate ±12%).
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.