MiniCPM V 4.7 1B DSpark — Hardware Requirements & GPU Compatibility
Chat
MiniCPM V 4.7 1B DSpark is a 214M-parameter open language model from OpenBMB in the MiniCPM family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 0.44 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 256K)Best on 24 GB (Q4_K_M · ~1489 tok/s · 256K)Macs from 32 GB (~191 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run MiniCPM V 4.7 1B DSpark
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/openbmb/MiniCPM-V-4.7-1B-DSpark-gguf:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 23.5 GB free · 16K context
Download: dspark-MiniCPM-V-4_7-1B-Q4_K_M.gguf0.13 GBopenbmb
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (11 GB headroom) · Q4_K_M
- Generation speed
- ~532 tok/s
- generation speed
- Cost per 1M output tokens
- $0.036
- per 1M output tokens
How Much VRAM Does MiniCPM V 4.7 1B DSpark Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.4 GB | 0.6 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~1638 tok/s | |
| 0.4 GB | 0.6 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~1598 tok/s | |
| 0.4 GB | 0.6 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 256K context · ~1560 tok/s | |
| 0.4 GB | 0.6 GB | 4-bit small — 4-bit small quantization | Fits: 256K context · ~1524 tok/s | |
| 0.4 GB | 0.6 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 256K context · ~1489 tok/s | |
| 0.5 GB | 0.6 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 256K context · ~1424 tok/s | |
| 0.5 GB | 0.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 256K context · ~1337 tok/s | |
| 0.5 GB | 0.7 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 256K context · ~1260 tok/s |
Selected Q4_K_M
4-bit medium quantization0.5GBat 16K context
- Weights
- 0.1 GB
- KV cache
- 0.1 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.5 GB free · ~1489 tok/s
≥50 tok/s needs ≥34 GB/s · RTX 5090 ~2647, RTX 3090 Ti ~1489
Which Hardware Can Run MiniCPM V 4.7 1B DSpark?
Q4_K_M · 0.4 GBMiniCPM V 4.7 1B DSpark (Q4_K_M) requires 0.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. Using the full 262K context window can add up to 1.3 GB, bringing total usage to 1.8 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 176 devices with unified memory can run MiniCPM V 4.7 1B DSpark, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
≤ 11 GB
≤ 11 GB tier →fits · 7.5 GB free · up to 256K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~1123Simulate output on RTX 3080RTX 2080 Ti~910Simulate output on RTX 2080 TiRTX 3070 Ti~899Simulate output on RTX 3070 TiM3*8 GB~163Simulate output on iMac 24" M3 (8 GB)Orin Nano~151Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~109Simulate output on iPhone 1720 GB
fits · 19.5 GB free · up to 256K ctx
1 GPU
RX 7900 XT~1091Simulate output on RX 7900 XT32–40 GB
fits · 31.5 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~2647Simulate output on RTX 5090M5 Max36 GB~732Simulate output on Mac Studio M5 Max (36 GB)M532 GB~244Simulate output on MacBook Air 13" M5 (32 GB)Orin~303Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~199Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to MiniCPM V 4.7 1B DSpark
MiniCPM family · 16 models →Similar models
5| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| LFM2.5 230MLiquid AI | — | 0.6 GB | ~1310 | same size |
| Pythia 160MEleutherAI | — | 0.1 GB | ~4680 | same size |
| Pythia 160M DedupedEleutherAI | — | 0.1 GB | ~4680 | same size |
| Japanese GPT Neox Smallrinna | — | 0.1 GB | ~5040 | same size |
| T5 Paraphrase PawsVamsi | — | 0.2 GB | ~4368 | same size |
Specifications
- Publisher
- OpenBMB
- Family
- MiniCPM
- Parameters
- 214M
- Architecture
- Qwen3DSparkModel
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,094
- Release Date
- 2026-10-08
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does MiniCPM V 4.7 1B DSpark need?
MiniCPM V 4.7 1B DSpark requires 0.4 GB of VRAM at Q4_K_M, or 0.7 GB at BF16. Full 262K context adds up to 1.3 GB (1.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 214M × 4.8 bits ÷ 8 = 0.1 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 1.7 GB (at full 262K context)
VRAM usage by quantization
What's the best quantization for MiniCPM V 4.7 1B DSpark?
For MiniCPM V 4.7 1B DSpark, Q4_K_M (0.4 GB) offers the best balance of quality and VRAM usage. Q5_0 (0.4 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run MiniCPM V 4.7 1B DSpark on a Mac?
Yes — Mac Mini M1 (8 GB) and 155 other Macs can run MiniCPM V 4.7 1B DSpark. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.4 GB of usable unified memory (RAM minus macOS overhead).
Can I run MiniCPM V 4.7 1B DSpark locally?
Yes — MiniCPM V 4.7 1B DSpark can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is MiniCPM V 4.7 1B DSpark?
At Q4_K_M, MiniCPM V 4.7 1B DSpark can reach ~10909 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1489 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 0.44 × 0.65 = ~11818 tok/s
Estimated speed at Q4_K_M (0.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of MiniCPM V 4.7 1B DSpark?
At Q4_K_M, the download is about 0.13 GB. The full-precision BF16 version is 0.43 GB. The smallest option (Q2_K) is 0.09 GB.
Which GPUs can run MiniCPM V 4.7 1B DSpark?
52 consumer GPUs can run MiniCPM V 4.7 1B DSpark at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run MiniCPM V 4.7 1B DSpark?
176 devices with unified memory can run MiniCPM V 4.7 1B DSpark at Q4_K_M (0.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.