Nanbeige4.2 3B — Hardware Requirements & GPU Compatibility
ChatFunctions
Nanbeige4.2 3B is a 4.2B-parameter open language model from Nanbeige. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 2.89 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 · 64K)Best on 24 GB (Q4_K_M · ~227 tok/s · 256K)Macs from 8 GB (Q4_K_M · ~25 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Nanbeige4.2 3B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.2-3B-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 20.5 GB free · 16K context
Download: Nanbeige_Nanbeige4.2-3B-Q4_K_M.gguf2.68 GBbartowski
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (8 GB headroom) · Q4_K_M
- Generation speed
- ~81 tok/s
- generation speed
- Cost per 1M output tokens
- $0.28
- per 1M output tokens
How Much VRAM Does Nanbeige4.2 3B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.2 GB | 3.5 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~303 tok/s | |
| 2.2 GB | 3.6 GB | 3-bit small — 3-bit small quantization | Fits: 256K context · ~295 tok/s | |
| 2.4 GB | 3.8 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~270 tok/s | |
| 2.5 GB | 3.9 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 256K context · ~264 tok/s | |
| 2.9 GB | 4.3 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 256K context · ~227 tok/s | |
| 3.4 GB | 4.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 256K context · ~195 tok/s | |
| 3.8 GB | 5.2 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 256K context · ~171 tok/s | |
| 4.6 GB | 5.9 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 256K context · ~144 tok/s |
Selected Q4_K_M
4-bit medium quantization3.5GBat 16K context
- Weights
- 2.5 GB
- KV cache
- 0.7 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 20.5 GB free · ~227 tok/s
≥50 tok/s needs ≥222 GB/s · RTX 5090 ~403, RTX 3090 Ti ~227
Which Hardware Can Run Nanbeige4.2 3B?
Q4_K_M · 2.9 GBNanbeige4.2 3B (Q4_K_M) requires 2.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. Using the full 262K context window can add up to 11.7 GB, bringing total usage to 14.6 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Nanbeige4.2 3B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 4.5 GB free · up to 64K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~171Simulate output on RTX 3080RTX 2080 Ti~139Simulate output on RTX 2080 TiRTX 3070 Ti~137Simulate output on RTX 3070 TiM3*8 GB~25Simulate output on iMac 24" M3 (8 GB)Orin Nano~23Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~17Simulate output on iPhone 1720 GB
fits · 16.5 GB free · up to 256K ctx
1 GPU
RX 7900 XT~166Simulate output on RX 7900 XT32–40 GB
fits · 28.5 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~403Simulate output on RTX 5090M5 Max36 GB~111Simulate output on Mac Studio M5 Max (36 GB)M532 GB~37Simulate output on MacBook Air 13" M5 (32 GB)Orin~46Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~30Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Gemma 3 4B ITGoogle | 64.0 | 5 GB | ~231 | same size |
| Granite Vision 4.1 4BIBM | — | 4 GB | ~228 | same size |
| Qwen3 VL 4B InstructAlibaba | — | 4.5 GB | ~208 | same size |
| MiniCPM V 4OpenBMB | — | 3.1 GB | ~236 | same size |
| Phi 3.5 Vision InstructMicrosoft | — | 9.2 GB | ~183 | same size |
| Gemma 4 E4B IT AssistantGoogle | — | 2.7 GB | ~243 | same size |
Specifications
- Publisher
- Nanbeige
- Parameters
- 4.2B
- Architecture
- NanbeigeForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 166,144
- Release Date
- 2026-07-21
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Nanbeige4.2 3B need?
Nanbeige4.2 3B requires 2.9 GB of VRAM at Q4_K_M, or 8.7 GB at BF16. Full 262K context adds up to 11.7 GB (14.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 4.2B × 4.8 bits ÷ 8 = 2.5 GB
KV Cache + Overhead ≈ 0.4 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 ≈ 12.1 GB (at full 262K context)
VRAM usage by quantization
What's the best quantization for Nanbeige4.2 3B?
For Nanbeige4.2 3B, Q4_K_M (2.9 GB) offers the best balance of quality and VRAM usage. Q4_K_L (3.0 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 1.5 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Nanbeige4.2 3B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Nanbeige4.2 3B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run Nanbeige4.2 3B locally?
Yes — Nanbeige4.2 3B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Nanbeige4.2 3B?
At Q4_K_M, Nanbeige4.2 3B can reach ~1661 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~227 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 ÷ 2.89 × 0.65 = ~1799 tok/s
Estimated speed at Q4_K_M (2.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Nanbeige4.2 3B?
At Q4_K_M, the download is about 2.50 GB. The full-precision BF16 version is 8.34 GB. The smallest option (IQ2_XXS) is 1.15 GB.
Which GPUs can run Nanbeige4.2 3B?
52 consumer GPUs can run Nanbeige4.2 3B 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 Nanbeige4.2 3B?
163 devices with unified memory can run Nanbeige4.2 3B at Q4_K_M (2.9 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.