Granite 3B Code Base 2k — Hardware Requirements & GPU Compatibility
ChatCode
Granite 3B Code Base 2k is a 3.5B-parameter open language model from IBM in the Granite family. It supports a context window of up to 2,048 tokens. At Q4_K_M it needs about 3.06 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 · 2K)Best on 24 GB (Q4_K_M · ~214 tok/s · 2K)Macs from 8 GB (Q4_K_M · ~23 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Granite 3B Code Base 2k
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve ibm-granite/granite-3b-code-base-2k --max-model-len 2048vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (8 GB headroom) · Q4_K_M
- Generation speed
- ~194 tok/s
- generation speed
- Cost per 1M output tokens
- $0.18
- per 1M output tokens
How Much VRAM Does Granite 3B Code Base 2k Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.5 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 2K context · ~267 tok/s | |
| 2.7 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 2K context · ~245 tok/s | |
| 3.1 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 2K context · ~214 tok/s | |
| 3.5 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 2K context · ~190 tok/s | |
| 3.8 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 2K context · ~171 tok/s | |
| 4.5 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 2K context · ~147 tok/s | |
| 7.9 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 2K context · ~83 tok/s |
Selected Q4_K_M
4-bit medium quantization3.1GBat 2K context
- Weights
- 2.1 GB
- KV cache
- 0.7 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 20.9 GB free · ~214 tok/s
≥50 tok/s needs ≥235 GB/s · RTX 5090 ~381, RTX 3090 Ti ~214
Which Hardware Can Run Granite 3B Code Base 2k?
Q4_K_M · 3.1 GBGranite 3B Code Base 2k (Q4_K_M) requires 3.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Granite 3B Code Base 2k, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), MacBook Air 13" M3 (8 GB).
≤ 11 GB
≤ 11 GB tier →fits · 4.9 GB free · up to 2K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~162Simulate output on RTX 3080RTX 2080 Ti~131Simulate output on RTX 2080 TiRTX 3070 Ti~129Simulate output on RTX 3070 TiM3*8 GB~23Simulate output on iMac 24" M3 (8 GB)Orin Nano~22Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~16Simulate output on iPhone 1720 GB
fits · 16.9 GB free · up to 2K ctx
1 GPU
RX 7900 XT~157Simulate output on RX 7900 XT32–40 GB
fits · 28.9 GB free · up to 2K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~381Simulate output on RTX 5090M5 Max36 GB~105Simulate output on Mac Studio M5 Max (36 GB)M532 GB~35Simulate output on MacBook Air 13" M5 (32 GB)Orin~44Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~29Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Granite 3B Code Base 2k
Granite family · 28 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Unlimited OCR 2Baidu | — | 3.3 GB | ~517 | same size |
| Jina Ocr V1jinaai | — | 3.3 GB | ~509 | same size |
| Unlimited OCRBaidu | — | 3.3 GB | ~519 | same size |
| DeepSeek OCR 2DeepSeek | — | 2.8 GB | ~504 | same size |
| Qwen2.5 VL 3B InstructAlibaba | — | 3.2 GB | ~249 | same size |
| Tiny Aya GlobalCohere | — | 9.4 GB | ~89 | same size |
Specifications
- Publisher
- IBM
- Family
- Granite
- Parameters
- 3.5B
- Architecture
- LlamaForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 49,152
- Release Date
- 2024-04-23
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Granite 3B Code Base 2k need?
Granite 3B Code Base 2k requires 3.1 GB of VRAM at Q4_K_M, or 7.9 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 3.5B × 4.8 bits ÷ 8 = 2.1 GB
KV Cache + Overhead ≈ 1 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.
VRAM usage by quantization
What's the best quantization for Granite 3B Code Base 2k?
For Granite 3B Code Base 2k, Q4_K_M (3.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (3.5 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 2.5 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Granite 3B Code Base 2k on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Granite 3B Code Base 2k. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 3.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run Granite 3B Code Base 2k locally?
Yes — Granite 3B Code Base 2k can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Granite 3B Code Base 2k?
At Q4_K_M, Granite 3B Code Base 2k can reach ~1569 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~214 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 ÷ 3.06 × 0.65 = ~1699 tok/s
Estimated speed at Q4_K_M (3.1 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Granite 3B Code Base 2k?
At Q4_K_M, the download is about 2.09 GB. The full-precision BF16 version is 6.97 GB. The smallest option (Q2_K) is 1.48 GB.
Which GPUs can run Granite 3B Code Base 2k?
52 consumer GPUs can run Granite 3B Code Base 2k 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 Granite 3B Code Base 2k?
163 devices with unified memory can run Granite 3B Code Base 2k at Q4_K_M (3.1 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.