Granite 4.1 30B — Hardware Requirements & GPU Compatibility
ChatFunctions
Granite 4.1 30B is IBM's 28.9-billion-parameter dense language model, tuned for chat, tool calling, and general assistant tasks as part of the Granite 4.1 family alongside smaller 3B and 8B variants. IBM built the 4.1 generation to be enterprise-friendly, with a focus on reliable tool calling and instruction following for agentic workflows. At this size, local inference calls for quantization and a capable GPU, fitting on a single high-end consumer or workstation card. The model supports a 131,072 token context window, enough for lengthy documents, codebases, or long multi-turn conversations. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use. Published in April 2026, it is the largest model in the Granite 4.1 generation, which succeeds Granite 4.0.
Decent on a 24 GB GPU
Runs from 16 GB (IQ3_XXS · 16K)Best on 24 GB (Q4_K_M · ~36 tok/s · 16K)Macs from 18 GB (IQ2_M · ~10 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Granite 4.1 30B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run granite4.1:30bQ4_K_M fits fully on the RTX 4090 · 2.1 GB free · 16K context
Download: granite-4.1-30b-Q4_K_M.gguf17.49 GBunsloth
Other ways
each opens step-by-stepRun in cloud
Fits on RTX PRO 4500 (32 GB) (10 GB headroom) · Q4_K_M
- Generation speed
- ~32 tok/s
- generation speed
- Cost per 1M output tokens
- $2.94
- per 1M output tokens
How Much VRAM Does Granite 4.1 30B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 13.1 GB | 21.2 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~50 tok/s | |
| 13.5 GB | 21.5 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~49 tok/s | |
| 14.9 GB | 23 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~44 tok/s | |
| 15.3 GB | 23.3 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~43 tok/s | |
| 18.2 GB | 26.2 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 16K context · ~36 tok/s | |
| 21.4 GB | 29.5 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 8K context · ~31 tok/s | |
| 24.6 GB | 32.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 28.4 GB | |
| 29.7 GB | 37.8 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 33.5 GB |
Selected Q4_K_M
4-bit medium quantization21.9GBat 16K context
- Weights
- 17.3 GB
- KV cache
- 4.3 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 2.1 GB free · ~36 tok/s
≥50 tok/s needs ≥1.40 TB/s · RTX 5090 ~64
Which Hardware Can Run Granite 4.1 30B?
Q4_K_M · 18.2 GBGranite 4.1 30B (Q4_K_M) requires 18.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 24+ GB is recommended. Using the full 131K context window can add up to 33.8 GB, bringing total usage to 52.0 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run Granite 4.1 30B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
tight · up to 8K ctx
1 GPU
RX 7900 XT~26Simulate output on RX 7900 XT32–40 GB
fits · 10.1 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~64Simulate output on RTX 5090M5 Max36 GB~18Simulate output on Mac Studio M5 Max (36 GB)M532 GB~6Simulate output on MacBook Air 13" M5 (32 GB)Orin~7Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~5Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Granite 4.1 30B?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
Here are all 2 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
Alternatives to Granite 4.1 30B
Granite family · 26 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.8 27BAlibaba | 122.1 | 17.9 GB | ~38 | same size |
| Qwen3.6 27BAlibaba | 111.2 | 17.9 GB | ~38 | same size |
| Qwen3.5 27BAlibaba | 103.8 | 17.9 GB | ~38 | same size |
| Hy Memory 30B A3BTencent | — | 19.1 GB | ~184 | same size |
| Muse Glimmer 30BMeta | — | 19.6 GB | ~36 | same size |
| Hy MT2 30B A3BTencent | — | 19.1 GB | ~170 | same size |
Specifications
- Publisher
- IBM
- Family
- Granite
- Parameters
- 28.9B
- Architecture
- GraniteForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 100,352
- Release Date
- 2026-04-06
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Granite 4.1 30B need?
Granite 4.1 30B requires 18.2 GB of VRAM at Q4_K_M, or 58.6 GB at BF16. Full 131K context adds up to 33.8 GB (52.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 28.9B × 4.8 bits ÷ 8 = 17.3 GB
KV Cache + Overhead ≈ 0.9 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 ≈ 34.7 GB (at full 131K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Granite 4.1 30B?
Yes, at Q5_K_L (21.8 GB) or lower. Higher quantizations like Q6_K (24.6 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Granite 4.1 30B?
For Granite 4.1 30B, Q4_K_M (18.2 GB) offers the best balance of quality and VRAM usage. Q4_K_L (18.5 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 8.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Granite 4.1 30B on a Mac?
Yes — MacBook Pro 14" M3 Pro (18 GB) and 108 other Macs can run Granite 4.1 30B, the smallest at IQ2_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 18.2 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).
Can I run Granite 4.1 30B locally?
Yes — Granite 4.1 30B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Granite 4.1 30B?
At Q4_K_M, Granite 4.1 30B can reach ~264 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~36 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 ÷ 18.2 × 0.65 = ~286 tok/s
Estimated speed at Q4_K_M (18.2 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Granite 4.1 30B?
At Q4_K_M, the download is about 17.32 GB. The full-precision BF16 version is 57.73 GB. The smallest option (IQ2_XXS) is 7.94 GB.
Which GPUs can run Granite 4.1 30B?
8 consumer GPUs can run Granite 4.1 30B at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Granite 4.1 30B?
122 devices with unified memory can run Granite 4.1 30B at Q4_K_M (18.2 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.