llmrun
IBMGraniteGraniteForCausalLM

Granite Guardian 4.1 8B — Hardware Requirements & GPU Compatibility

ChatFunctions

Granite Guardian 4.1 8B is a 8.4B-parameter open language model from IBM in the Granite family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 5.66 GB of VRAM — see which GPUs and Macs can run it below.

8.4B params · dense131K contextApache 2.054.8K downloads51 likes3.7K quant downloads
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 8KBest on24 GB Q4_K_M · ~116 tok/s · 64KMacs from16 GB Q4_K_M · ~25 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Granite Guardian 4.1 8B

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
one command · needs Ollama installed
$ollama run granite4.1-guardian:8b-q4_K_M

Q4_K_M fits fully on the RTX 4090 · 16.0 GB free · 16K context

Download: granite-guardian-4.1-8b-Q4_K_M.gguf5.12 GBibm-granite

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Runs on RTX 3080 (10 GB) (2 GB headroom) · Q4_K_M

Generation speed
~87 tok/s
generation speed
Cost per 1M output tokens
$0.39
per 1M output tokens

How Much VRAM Does Granite Guardian 4.1 8B Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn RTX 4090 (reference)
4.2 GB9.2 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 64K context · ~156 tok/s
4.3 GB9.3 GB3-bit small — 3-bit small quantizationFits: 64K context · ~152 tok/s
4.7 GB9.8 GB3-bit medium — 3-bit medium quantizationFits: 64K context · ~139 tok/s
4.8 GB9.9 GB4-bit · legacy — 4-bit legacy quantizationFits: 64K context · ~136 tok/s
5.7 GB10.7 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 64K context · ~116 tok/s
6.6 GB11.6 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 64K context · ~99 tok/s
7.5 GB12.6 GB6-bit, very good — 6-bit quantization, very good qualityFits: 64K context · ~87 tok/s
9.0 GB14.1 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 64K context · ~73 tok/s

Selected Q4_K_M

4-bit medium quantization

8.0GBat 16K context

Weights
5.0 GB
KV cache
2.7 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 16.0 GB free · ~116 tok/s

≥50 tok/s needs ≥435 GB/s · RTX 5090 ~206, M5 Ultra ~152

Which Hardware Can Run Granite Guardian 4.1 8B?

Q4_K_M · 5.7 GB

Granite Guardian 4.1 8B (Q4_K_M) requires 5.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. Using the full 131K context window can add up to 21.1 GB, bringing total usage to 26.8 GB. 107 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 172 devices with unified memory can run Granite Guardian 4.1 8B, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB), NVIDIA Jetson Orin Nano 8GB (Super).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Q4_K_M · 8 GB · ~31 tok/s · 8Ktight8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 8 GB · ~41 tok/s · 32K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 8 GB · ~51 tok/s · 32K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 8 GB · ~116 tok/s · 64K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 8 GB · ~15 tok/s · 128KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 8 GB · ~68 tok/s · 128KMacs →

Alternatives to Granite Guardian 4.1 8B

Granite family · 28 models →

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
ALoDLM 8BAmazon—7.6 GB~119same size
Llm Jp 4.1 8B Thinkingllm-jp—7.6 GB~115same size
Ling 3.0 TinyInclusion AI—5.5 GB~364same size
Apertus V1.5 8Bswiss-ai—8.5 GB~111same size
LFM2.5 8B A1BLiquid AI—5.6 GB~335same size
BitCPM CANN 8BOpenBMB—5.6 GB~127same size

Specifications

Publisher
IBM
Family
Granite
Parameters
8.4B
Architecture
GraniteForCausalLM
Context Length
131,072 tokens
Vocabulary Size
100,352
Release Date
2026-04-16
License
Apache 2.0

Frequently Asked Questions

How much VRAM does Granite Guardian 4.1 8B need?

Granite Guardian 4.1 8B requires 5.7 GB of VRAM at Q4_K_M, or 17.4 GB at BF16. Full 131K context adds up to 21.1 GB (26.8 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 8.4B × 4.8 bits ÷ 8 = 5 GB

KV Cache + Overhead ≈ 0.7 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 ≈ 21.8 GB (at full 131K context)

VRAM usage by quantization

5.7 GB
26.8 GB

Learn more about VRAM estimation →

What's the best quantization for Granite Guardian 4.1 8B?

For Granite Guardian 4.1 8B, Q4_K_M (5.7 GB) offers the best balance of quality and VRAM usage. Q5_0 (5.9 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 2.9 GB.

VRAM requirement by quantization

IQ2_XXS
2.9 GB
IQ3_XS
4.1 GB
Q3_K_L
4.9 GB
Q4_K_M ★
5.7 GB
Q5_0
5.9 GB
BF16
17.4 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Granite Guardian 4.1 8B on a Mac?

Yes — Mac Mini M2 Pro (16 GB) and 145 other Macs can run Granite Guardian 4.1 8B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 5.7 GB of usable unified memory (RAM minus macOS overhead).

Can I run Granite Guardian 4.1 8B locally?

Yes — Granite Guardian 4.1 8B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Granite Guardian 4.1 8B?

At Q4_K_M, Granite Guardian 4.1 8B can reach ~848 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~116 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 ÷ 5.66 × 0.65 = ~919 tok/s

Estimated speed at Q4_K_M (5.7 GB)

~919 tok/s
~116 tok/s
~919 tok/s
~848 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of Granite Guardian 4.1 8B?

At Q4_K_M, the download is about 5.03 GB. The full-precision BF16 version is 16.76 GB. The smallest option (IQ2_XXS) is 2.30 GB.

Which GPUs can run Granite Guardian 4.1 8B?

107 consumer GPUs can run Granite Guardian 4.1 8B at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6700M, AMD Radeon RX 6750 XT, AMD Radeon RX 5600 XT. 51 GPUs have plenty of headroom for comfortable inference.

Which devices can run Granite Guardian 4.1 8B?

172 devices with unified memory can run Granite Guardian 4.1 8B at Q4_K_M (5.7 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.