Granite 3.0 1B A400m Instruct — Hardware Requirements & GPU Compatibility
ChatFunctions
Granite 3.0 1B A400m Instruct is a 1.3B-parameter open language model from IBM in the Granite family. It supports a context window of up to 4,096 tokens. At Q4_K_M it needs about 1.20 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 · 4K)Best on 24 GB (Q4_K_M · ~524 tok/s · 4K)Macs from 8 GB (Q4_K_M · ~98 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Granite 3.0 1B A400m Instruct
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
ollama run hf.co/bartowski/granite-3.0-1b-a400m-instruct-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 22.7 GB free · 4K context
Download: granite-3.0-1b-a400m-instruct-Q4_K_M.gguf0.82 GBbartowski
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 3060 12GB (10 GB headroom) · Q4_K_M
- Generation speed
- ~337 tok/s
- generation speed
- Cost per 1M output tokens
- $0.051
- per 1M output tokens
How Much VRAM Does Granite 3.0 1B A400m Instruct Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.0 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 4K context · ~557 tok/s | |
| 1.0 GB | — | 3-bit small — 3-bit small quantization | Fits: 4K context · ~555 tok/s | |
| 1.1 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 4K context · ~545 tok/s | |
| 1.1 GB | — | 4-bit · legacy — 4-bit legacy quantization | Fits: 4K context · ~542 tok/s | |
| 1.2 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 4K context · ~524 tok/s | |
| 1.4 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 4K context · ~505 tok/s | |
| 1.5 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 4K context · ~487 tok/s | |
| 1.7 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 4K context · ~460 tok/s |
Selected Q4_K_M
4-bit medium quantization1.3GBat 4K context
- Weights
- 0.8 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 22.7 GB free · ~524 tok/s
≥50 tok/s needs ≥32 GB/s · RTX 5090 ~606, RTX 3090 Ti ~524
Which Hardware Can Run Granite 3.0 1B A400m Instruct?
Q4_K_M · 1.2 GBGranite 3.0 1B A400m Instruct (Q4_K_M) requires 1.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2+ GB is recommended. Using the full 4K context window can add up to 0.1 GB, bringing total usage to 1.3 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Granite 3.0 1B A400m Instruct, including NVIDIA DGX Spark, NVIDIA Jetson AGX Thor Developer Kit.
≤ 11 GB
≤ 11 GB tier →fits · 6.7 GB free · up to 4K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~476Simulate output on RTX 3080RTX 2080 Ti~438Simulate output on RTX 2080 TiRTX 3070 Ti~436Simulate output on RTX 3070 TiM3*8 GB~98Simulate output on iMac 24" M3 (8 GB)Orin Nano~140Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~78Simulate output on iPhone 1720 GB
fits · 18.7 GB free · up to 4K ctx
1 GPU
RX 7900 XT~179Simulate output on RX 7900 XT32–40 GB
fits · 30.7 GB free · up to 4K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~606Simulate output on RTX 5090M5 Max36 GB~167Simulate output on Mac Studio M5 Max (36 GB)M532 GB~119Simulate output on MacBook Air 13" M5 (32 GB)Orin~237Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~147Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Granite 3.0 1B A400m Instruct
Granite family · 28 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM V 4.6 ThinkingOpenBMB | — | 1.5 GB | ~580 | same size |
| Llama 3.2 1B InstructMeta | — | 2.3 GB | ~799 | same size |
| Inkling Small DSpark PreviewRadixArk | — | 1.5 GB | ~555 | same size |
| Sweep Next Edit 1.5BXenova | — | 1.6 GB | ~551 | same size |
| Ouro 1.4BByteDance | — | 6.4 GB | ~184 | same size |
| Ilama 3.2 1Bhmellor | — | 3.3 GB | ~231 | same size |
Specifications
- Publisher
- IBM
- Family
- Granite
- Parameters
- 1.3B
- Active parameters
- 0.4B per token
- Architecture
- GraniteMoeForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 49,155
- Release Date
- 2024-10-03
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Granite 3.0 1B A400m Instruct need?
Granite 3.0 1B A400m Instruct requires 1.2 GB of VRAM at Q4_K_M, or 3.1 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 1.3B × 4.8 bits ÷ 8 = 0.8 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 ≈ 0.5 GB (at full 4K context)
VRAM usage by quantization
What's the best quantization for Granite 3.0 1B A400m Instruct?
For Granite 3.0 1B A400m Instruct, Q4_K_M (1.2 GB) offers the best balance of quality and VRAM usage. Q4_K_L (1.2 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 0.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Granite 3.0 1B A400m Instruct on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Granite 3.0 1B A400m Instruct. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.2 GB of usable unified memory (RAM minus macOS overhead).
Can I run Granite 3.0 1B A400m Instruct locally?
Yes — Granite 3.0 1B A400m Instruct can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Granite 3.0 1B A400m Instruct?
At Q4_K_M, Granite 3.0 1B A400m Instruct can reach ~205 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~524 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 0.4 GB active ÷ (8000 × 0.65) = 0.074 ms, plus 24 layers × 0.055 ms = 1.320 ms, so 1000 ÷ 1.394 ms = ~717 tok/s
Estimated speed at Q4_K_M (1.2 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Granite 3.0 1B A400m Instruct?
At Q4_K_M, the download is about 0.80 GB. The full-precision BF16 version is 2.67 GB. The smallest option (IQ2_XXS) is 0.37 GB.
Which GPUs can run Granite 3.0 1B A400m Instruct?
52 consumer GPUs can run Granite 3.0 1B A400m Instruct 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 3.0 1B A400m Instruct?
163 devices with unified memory can run Granite 3.0 1B A400m Instruct at Q4_K_M (1.2 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.