Granite 4.0 350M — Hardware Requirements & GPU Compatibility
ChatFunctionsGranite 4.0 350M is IBM's instruct model containing 350 million parameters; it is the smallest member of the Granite 4.0 Nano group, finetuned from Granite-4.0-350M-Base via supervised finetuning, reinforcement learning and model merging. Designed for lightweight assistant tasks, it handles tool calling, fill-in-the-middle code completion, and supports twelve languages, including English, German, Japanese, Arabic, and Chinese. Its config employs a hybrid architecture (GraniteMoeHybrid). Given this size, it runs on a CPU, phone-class devices, or small GPUs without quantization, making it suitable for edge and on-device use. The context window holds 32,768 tokens. Released under the Apache 2.0 license, it allows unrestricted commercial and research usage. The Hub repository appeared in October 2025, with the card listing a release date of October 28, 2025. This model is the smaller sibling of Granite 4.0 1B, and the card notes that users can fine-tune these Nano models to add languages beyond the supported list.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 32K)Best on 24 GB (Q4_K_M · ~1150 tok/s · 32K)Macs from 8 GB (Q4_K_M · ~126 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Granite 4.0 350M
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/ibm-granite/granite-4.0-350m-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 23.0 GB free · 16K context
Download: granite-4.0-350m-Q4_K_M.gguf0.24 GBibm-granite
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3060 12GB (11 GB headroom) · Q4_K_M
- Generation speed
- ~411 tok/s
- generation speed
- Cost per 1M output tokens
- $0.043
- per 1M output tokens
How Much VRAM Does Granite 4.0 350M Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.5 GB | 1.4 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~1285 tok/s | |
| 0.5 GB | 1.4 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~1285 tok/s | |
| 0.5 GB | 1.4 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~1236 tok/s | |
| 0.5 GB | 1.4 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~1236 tok/s | |
| 0.6 GB | 1.5 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~1150 tok/s | |
| 0.6 GB | 1.5 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~1074 tok/s | |
| 0.7 GB | 1.5 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~1008 tok/s | |
| 0.7 GB | 1.6 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~923 tok/s |
Selected Q4_K_M
4-bit medium quantization1.0GBat 16K context
- Weights
- 0.2 GB
- KV cache
- 0.5 GB
- Overhead
- 0.3 GB
Which Hardware Can Run Granite 4.0 350M?
Q4_K_M · 0.6 GBGranite 4.0 350M (Q4_K_M) requires 0.6 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 33K context window can add up to 0.9 GB, bringing total usage to 1.4 GB. 114 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 185 devices with unified memory can run Granite 4.0 350M, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB).
≤ 11 GB
≤ 11 GB tier →fits · 3.0 GB free · up to 32K ctx
68 GPUs · 1 Mac class · 3 device families
RTX 3080~867Simulate output on RTX 3080RTX 2080 Ti~703Simulate output on RTX 2080 TiRTX 3070 Ti~694Simulate output on RTX 3070 TiM3*8 GB~126Simulate output on iMac 24" M3 (8 GB)Orin Nano~116Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~84Simulate output on iPhone 1720 GB
fits · 19.0 GB free · up to 32K ctx
1 GPU
RX 7900 XT~842Simulate output on RX 7900 XT32–40 GB
fits · 31.0 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 9 device families
RTX 5090~2044Simulate output on RTX 5090M5 Max*36 GB~565Simulate output on Mac Studio M5 Max (36 GB)M632 GB~209Simulate output on iMac 24" M6 (32 GB)RTX Spark N1X~343Simulate output on NVIDIA RTX Spark N1X Laptop (32 GB)Orin~234Simulate output on NVIDIA Jetson AGX Orin 32GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Granite 4.0 350M?
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 3 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
- GPQA Diamond
Epoch AI · Oct 2025Independent
Independent11.2%
#99/100 open
- AIME 2024/2025
Epoch AI · Oct 2025Independent
Independent0.3%
#86/88 open
- CritPt
Epoch AI · Oct 2025Lab-reported
Lab-reported0.0%
#61/85 open
Alternatives to Granite 4.0 350M
Granite family · 28 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| SmolLM 360MHugging Face | — | 0.6 GB | ~1092 | same size |
| LFM2.5 350MLiquid AI | — | 0.8 GB | ~1130 | same size |
| MobileLLM R1 360MMeta | — | 1.3 GB | ~2730 | same size |
| ERNIE 4.5 0.3B PTBaidu | — | 0.7 GB | ~1213 | same size |
| Opt 350MMeta | — | 0.8 GB | ~851 | same size |
| Codegen 350M MonoSalesforce | — | 0.8 GB | ~851 | same size |
Specifications
- Publisher
- IBM
- Family
- Granite
- Parameters
- 352M
- Architecture
- GraniteMoeHybridForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 100,352
- Release Date
- 2025-10-07
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Granite 4.0 350M need?
Granite 4.0 350M requires 0.6 GB of VRAM at Q4_K_M, or 1.1 GB at BF16. Full 33K context adds up to 0.9 GB (1.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 352M × 4.8 bits ÷ 8 = 0.2 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 ≈ 1.3 GB (at full 33K context)
VRAM usage by quantization
What's the best quantization for Granite 4.0 350M?
For Granite 4.0 350M, Q4_K_M (0.6 GB) offers the best balance of quality and VRAM usage. Q5_0 (0.6 GB) provides better quality if you have the VRAM. The smallest option is IQ3_XXS at 0.5 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Granite 4.0 350M on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 158 other Macs can run Granite 4.0 350M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run Granite 4.0 350M locally?
Yes — Granite 4.0 350M can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Granite 4.0 350M?
At Q4_K_M, Granite 4.0 350M can reach ~8421 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1150 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 ÷ 0.57 × 0.65 = ~9123 tok/s
Estimated speed at Q4_K_M (0.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Granite 4.0 350M?
At Q4_K_M, the download is about 0.21 GB. The full-precision BF16 version is 0.70 GB. The smallest option (IQ3_XXS) is 0.14 GB.
Which GPUs can run Granite 4.0 350M?
114 consumer GPUs can run Granite 4.0 350M at Q4_K_M. Top options include AMD Radeon RX 5600 XT, AMD Radeon RX 5700 XT, AMD Radeon RX 580 8GB. 114 GPUs have plenty of headroom for comfortable inference.
Which devices can run Granite 4.0 350M?
185 devices with unified memory can run Granite 4.0 350M at Q4_K_M (0.6 GB), including AMD Ryzen 7 8845HS (Hawk Point) Laptop, AMD Ryzen AI 7 350 (Krackan Point) Laptop, AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.