MiniCPM5 1B hardware requirements
What is MiniCPM5 1B?
MiniCPM5 1B is the first model in OpenBMB's MiniCPM5 series, released in May 2026. Its model card aims it at on-device and local use and names tool use, code generation and harder reasoning as strengths. The same checkpoint can answer with or without a thinking step, and official GGUF files are available for llama.cpp, Ollama and LM Studio.
About the model
- Parameters
- 1.08B
- Attention
- Full attention
- Max context
- 131,072 tokens
- Released
- 2026-05-21
- Model card
- MiniCPM5 1B 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 1Bthis model | 1.08B | Q4_K_M | 1.3 GB | Runs great | Runs great | Runs great |
| MiniCPM5 2B | 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 | 0.69 GB | Good balance | Official GGUF · openbmb |
| Q8_0 | 1.15 GB | Near-lossless | Official GGUF · openbmb |
Memory needed by quant and context
| Quant | 4k | 8k | 16k | 32k | 64k | 128k |
|---|---|---|---|---|---|---|
| Q4_K_M | 1.2 | 1.3 | 1.6 | 2.2 | 3.3 | 5.5 |
| Q8_0 | 1.6 | 1.7 | 2.0 | 2.5 | 3.6 | 5.9 |
Which GPUs can run MiniCPM5 1B?
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. 1,407.3 tok/s1,238.5–1,576.2calibrated estimate ±12% | Q4_K_M | 1.9 / 32.0 GB | Full GPU | up to 128k | — | $4,200 street (as of 2026-08-09) |
| NVIDIA RTX PRO 6000 Blackwell | Runs great | est. 1,407.3 tok/s1,238.5–1,576.2calibrated estimate ±12% | Q4_K_M | 1.9 / 96.0 GB | Full GPU | up to 128k | — | — |
| NVIDIA RTX PRO 6000 Blackwell Max-Q | Runs great | est. 1,407.3 tok/s1,238.5–1,576.2calibrated estimate ±12% | Q4_K_M | 1.9 / 96.0 GB | Full GPU | up to 128k | — | — |
| Radeon RX 7900 XTX | Runs great | est. 818.6 tok/s720.3–916.8calibrated estimate ±12% | Q4_K_M | 1.9 / 24.0 GB | Full GPU | up to 128k | — | $999 launch MSRP |
| GeForce RTX 3090 Ti | Runs great | est. 791.6 tok/s696.6–886.6calibrated estimate ±12% | Q4_K_M | 1.9 / 24.0 GB | Full GPU | up to 128k | — | $1,999 launch MSRP |
| GeForce RTX 4090 | Runs great | est. 791.6 tok/s696.6–886.6calibrated estimate ±12% | Q4_K_M | 1.9 / 24.0 GB | Full GPU | up to 128k | — | $2,755 street (as of 2026-08-09) |
| Apple M5 Ultra · 96 GB | Runs great | est. 785.3 tok/s628.2–942.4calibrated estimate ±20% | Q4_K_M | 1.5 / 67.2 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 5080 | Runs great | est. 753.9 tok/s663.5–844.4calibrated estimate ±12% | Q4_K_M | 1.9 / 16.0 GB | Full GPU | up to 128k | — | $1,256 street (as of 2026-08-09) |
| GeForce RTX 3090 | Runs great | est. 735.1 tok/s646.9–823.3calibrated estimate ±12% | Q4_K_M | 1.9 / 24.0 GB | Full GPU | up to 128k | — | $1,050 street (as of 2026-08-09) |
| GeForce RTX 3080 12GB | Runs great | est. 716.2 tok/s630.3–802.2calibrated estimate ±12% | Q4_K_M | 1.9 / 12.0 GB | Full GPU | up to 128k | — | $799 launch MSRP |
| GeForce RTX 5070 Ti | Runs great | est. 703.7 tok/s619.2–788.1calibrated estimate ±12% | Q4_K_M | 1.9 / 16.0 GB | Full GPU | up to 128k | — | $949 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Runs great | est. 703.7 tok/s619.2–788.1calibrated estimate ±12% | Q4_K_M | 1.9 / 16.0 GB | Full GPU | up to 128k | — | — |
| GeForce RTX 5090 Laptop | Runs great | est. 703.7 tok/s619.2–788.1calibrated estimate ±12% | Q4_K_M | 1.9 / 24.0 GB | Full GPU | up to 128k | — | — |
| Radeon RX 7900 XT | Runs great | est. 682.1 tok/s600.3–764.0calibrated estimate ±12% | Q4_K_M | 1.9 / 20.0 GB | Full GPU | up to 128k | — | $899 launch MSRP |
| GeForce RTX 3080 10GB | Runs great | est. 596.9 tok/s525.2–668.5calibrated estimate ±12% | Q4_K_M | 1.9 / 10.0 GB | Full GPU | up to 128k | — | $699 launch MSRP |
| GeForce RTX 4080 Super | Runs great | est. 578.0 tok/s508.7–647.4calibrated estimate ±12% | Q4_K_M | 1.9 / 16.0 GB | Full GPU | up to 128k | — | $999 launch MSRP |
| GeForce RTX 4080 | Runs great | est. 563.1 tok/s495.5–630.7calibrated estimate ±12% | Q4_K_M | 1.9 / 16.0 GB | Full GPU | up to 128k | — | $1,199 launch MSRP |
| Radeon RX 9070 | Runs great | est. 550.0 tok/s484.0–616.0calibrated estimate ±12% | Q4_K_M | 1.9 / 16.0 GB | Full GPU | up to 128k | — | $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Runs great | est. 550.0 tok/s484.0–616.0calibrated estimate ±12% | Q4_K_M | 1.9 / 16.0 GB | Full GPU | up to 128k | — | $689 street (as of 2026-08-09) |
| Radeon RX 7800 XT | Runs great | est. 532.1 tok/s468.2–595.9calibrated estimate ±12% | Q4_K_M | 1.9 / 16.0 GB | Full GPU | up to 128k | — | $499 launch MSRP |
| GeForce RTX 4070 Ti Super | Runs great | est. 527.8 tok/s464.4–591.1calibrated estimate ±12% | Q4_K_M | 1.9 / 16.0 GB | Full GPU | up to 128k | — | $799 launch MSRP |
| GeForce RTX 5070 | Runs great | est. 527.8 tok/s464.4–591.1calibrated estimate ±12% | Q4_K_M | 1.9 / 12.0 GB | Full GPU | up to 128k | — | $629 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Runs great | est. 527.8 tok/s464.4–591.1calibrated estimate ±12% | Q4_K_M | 1.9 / 12.0 GB | Full GPU | up to 128k | — | — |
| Apple M3 Ultra · 96 GB | Runs great | est. 523.7 tok/s419.0–628.5calibrated estimate ±20% | Q4_K_M | 1.5 / 67.2 GB | Unified memory | up to 128k | — | — |
| Apple M5 Max (40-core GPU) · 48 GB | Runs great | est. 523.5 tok/s418.8–628.2calibrated estimate ±20% | Q4_K_M | 1.5 / 33.6 GB | Unified memory | up to 128k | — | — |
| Apple M2 Ultra · 64 GB | Runs great | est. 511.6 tok/s409.3–613.9calibrated estimate ±20% | Q4_K_M | 1.5 / 44.8 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 2080 Ti | Runs great | est. 483.8 tok/s425.7–541.8calibrated estimate ±12% | Q4_K_M | 1.9 / 11.0 GB | Full GPU | up to 128k | — | $999 launch MSRP |
| Apple M4 Max (40-core GPU) · 48 GB | Runs great | est. 465.6 tok/s372.4–558.7calibrated estimate ±20% | Q4_K_M | 1.5 / 33.6 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 4090 Laptop | Runs great | est. 452.4 tok/s398.1–506.6calibrated estimate ±12% | Q4_K_M | 1.9 / 16.0 GB | Full GPU | up to 128k | — | — |
| GeForce RTX 4070 | Runs great | est. 395.8 tok/s348.3–443.3calibrated estimate ±12% | Q4_K_M | 1.9 / 12.0 GB | Full GPU | up to 128k | — | $599 launch MSRP |
| GeForce RTX 4070 Super | Runs great | est. 395.8 tok/s348.3–443.3calibrated estimate ±12% | Q4_K_M | 1.9 / 12.0 GB | Full GPU | up to 128k | — | $599 launch MSRP |
| Apple M5 Max (32-core GPU) · 36 GB | Runs great | est. 392.2 tok/s313.8–470.7calibrated estimate ±20% | Q4_K_M | 1.5 / 25.2 GB | Unified memory | up to 128k | — | — |
| GeForce GTX 1080 Ti | Runs great | est. 380.1 tok/s266.1–494.1theoretical estimate ±30% | Q4_K_M | 1.9 / 11.0 GB | Full GPU | up to 128k | — | $699 launch MSRP |
| GeForce RTX 3070 | Runs great | est. 351.8 tok/s309.6–394.1calibrated estimate ±12% | Q4_K_M | 1.9 / 8.0 GB | Full GPU | up to 128k | — | $499 launch MSRP |
| GeForce RTX 5060 | Runs great | est. 351.8 tok/s309.6–394.1calibrated estimate ±12% | Q4_K_M | 1.9 / 8.0 GB | Full GPU | up to 128k | — | $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 16GB | Runs great | est. 351.8 tok/s309.6–394.1calibrated estimate ±12% | Q4_K_M | 1.9 / 16.0 GB | Full GPU | up to 128k | — | $569 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 8GB | Runs great | est. 351.8 tok/s309.6–394.1calibrated estimate ±12% | Q4_K_M | 1.9 / 8.0 GB | Full GPU | up to 128k | — | $429 street (as of 2026-08-09) |
| Apple M4 Max (32-core GPU) · 36 GB | Runs great | est. 349.6 tok/s279.7–419.5calibrated estimate ±20% | Q4_K_M | 1.5 / 25.2 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 4080 Laptop | Runs great | est. 339.3 tok/s298.6–380.0calibrated estimate ±12% | Q4_K_M | 1.9 / 12.0 GB | Full GPU | up to 128k | — | — |
| Intel Arc B580 | Runs great | est. 301.8 tok/s241.5–362.2calibrated estimate ±20% | Q4_K_M | 1.9 / 12.0 GB | Full GPU | up to 128k | — | $290 street (as of 2026-08-09) |
| GeForce RTX 3060 12GB | Runs great | est. 282.7 tok/s248.8–316.7calibrated estimate ±12% | Q4_K_M | 1.9 / 12.0 GB | Full GPU | up to 128k | — | $250 street (as of 2026-08-09) |
| Radeon RX 9060 XT 16GB | Runs great | est. 274.6 tok/s241.6–307.5calibrated estimate ±12% | Q4_K_M | 1.9 / 16.0 GB | Full GPU | up to 128k | — | $449 street (as of 2026-08-09) |
| Apple M5 Pro · 24 GB | Runs great | est. 261.8 tok/s209.4–314.1calibrated estimate ±20% | Q4_K_M | 1.5 / 16.8 GB | Unified memory | up to 128k | — | — |
| NVIDIA DGX Spark · 128 GB | Runs great | est. 238.9 tok/s191.1–286.7calibrated estimate ±20% | Q4_K_M | 1.5 / 116.9 GB | Unified memory | up to 128k | — | $3,999 launch MSRP (128 GB) |
| Ryzen AI Max+ 395 (Strix Halo) · 32 GB | Runs great | est. 235.5 tok/s188.4–282.6calibrated estimate ±20% | Q4_K_M | 1.5 / 22.4 GB | Unified memory | up to 128k | — | $1,999 launch MSRP (128 GB) |
| Apple M4 Pro · 24 GB | Runs great | est. 232.8 tok/s186.2–279.3calibrated estimate ±20% | Q4_K_M | 1.5 / 16.8 GB | Unified memory | up to 128k | — | — |
| GeForce RTX 4060 Ti 16GB | Runs great | est. 226.2 tok/s199.0–253.3calibrated estimate ±12% | Q4_K_M | 1.9 / 16.0 GB | Full GPU | up to 128k | — | $499 launch MSRP |
| GeForce RTX 4060 Ti 8GB | Runs great | est. 226.2 tok/s199.0–253.3calibrated estimate ±12% | Q4_K_M | 1.9 / 8.0 GB | Full GPU | up to 128k | — | $399 launch MSRP |
| GeForce RTX 4060 | Runs great | est. 213.6 tok/s188.0–239.2calibrated estimate ±12% | Q4_K_M | 1.9 / 8.0 GB | Full GPU | up to 128k | — | $299 launch MSRP |
| GeForce RTX 4060 Laptop | Runs great | est. 201.0 tok/s176.9–225.2calibrated estimate ±12% | Q4_K_M | 1.9 / 8.0 GB | Full GPU | up to 128k | — | — |
| GeForce RTX 4070 Laptop | Runs great | est. 201.0 tok/s176.9–225.2calibrated estimate ±12% | Q4_K_M | 1.9 / 8.0 GB | Full GPU | up to 128k | — | — |
| GeForce RTX 3050 8GB | Runs great | est. 175.9 tok/s154.8–197.0calibrated estimate ±12% | Q4_K_M | 1.9 / 8.0 GB | Full GPU | up to 128k | — | $249 launch MSRP |
| Apple M5 · 16 GB | Runs great | est. 131.0 tok/s104.8–157.2calibrated estimate ±20% | Q4_K_M | 1.5 / 11.2 GB | Unified memory | up to 64k | — | — |
| Apple M6 · 16 GB | Runs great | est. 131.0 tok/s104.8–157.2calibrated estimate ±20% | Q4_K_M | 1.5 / 11.2 GB | Unified memory | up to 64k | — | — |
| Apple M4 · 16 GB | Runs great | est. 102.3 tok/s81.9–122.8calibrated estimate ±20% | Q4_K_M | 1.5 / 11.2 GB | Unified memory | up to 64k | — | — |
| DDR5-6000 dual-channel CPU · 16 GB | Runs slowly | est. 53.9 tok/s43.1–64.6calibrated estimate ±20% | Q4_K_M | 0.9 GB RAM | CPU only | up to 128k |
| — |
| DDR5-5600 dual-channel CPU · 16 GB | Runs slowly | est. 50.3 tok/s40.2–60.3calibrated estimate ±20% | Q4_K_M | 0.9 GB RAM | CPU only | up to 128k |
| — |
| DDR4-3200 dual-channel CPU · 16 GB | Runs slowly | est. 28.7 tok/s23.0–34.5calibrated estimate ±20% | Q4_K_M | 0.9 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. 282.7 tok/s (248.8–316.7, calibrated estimate ±12%).
Measured results for MiniCPM5 1B
No public measurements for this model yet.
Frequently asked questions
How much VRAM does MiniCPM5 1B need?
At Q4_K_M the file is 0.69 GB; with 8k context a graphics card needs about 1.3 GB (weights 0.57 GB, KV cache 0.2 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 1B well?
Cheapest that runs it great: GeForce RTX 3060 12GB at $250 (street price as of 2026-08-09), est. 282.7 tok/s (248.8–316.7, calibrated estimate ±12%).
Can MiniCPM5 1B run on an 8 GB, 16 GB or 24 GB GPU?
At Q4_K_M with 8k context: GeForce RTX 4060 — Runs great, est. 213.6 tok/s (188.0–239.2, calibrated estimate ±12%); GeForce RTX 5060 Ti 16GB — Runs great, est. 351.8 tok/s (309.6–394.1, calibrated estimate ±12%); GeForce RTX 3090 — Runs great, est. 735.1 tok/s (646.9–823.3, 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.