llmrun
InternLMQwen3_5ForConditionalGeneration

Intern Decision 4B — Hardware Requirements & GPU Compatibility

VisionFunctions

Intern-Decision-4B is InternLM's 4.5-billion-parameter multimodal structured decision model, fine-tuned from Qwen3.5-4B. It accepts a shared state, a schema of named questions and optional images, and returns an answer distribution for every question in one forward pass by scoring candidate option symbols instead of sampling text. The card reports an average of 90.02 across its decision benchmarks, the highest in its family table, with roughly 44 ms per query on a single RTX 4090. At this size it fits on a single consumer GPU, including mid-range cards. The model supports a 262,144 token context window. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in September 2026. It is the largest of the Intern-Decision models listed in the card, alongside 0.8B and 2B siblings, and it depends on the custom inference code in the repository rather than a standard chat workflow.

4.5B params · dense262K contextApache 2.05.1K downloads95 likes1.9K quant downloads
Based on Qwen3.5 4B
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 128KBest on24 GB Q4_K_M · ~205 tok/s · 256KMacs from8 GB Q4_K_M · ~23 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Intern Decision 4B

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 hf.co/yeaay/Intern-Decision-4B-GGUF:Q4_K_M

Q4_K_M fits fully on the RTX 4090 · 20.6 GB free · 16K context

Download: Intern-Decision-4B-Q4_K_M.gguf2.71 GByeaay

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Runs on RTX 3060 12GB (8 GB headroom) · Q4_K_M

Generation speed
~73 tok/s
generation speed
Cost per 1M output tokens
$0.24
per 1M output tokens

How Much VRAM Does Intern Decision 4B Need?

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

QuantizationVRAM+32KOn RTX 4090 (reference)
2.4 GB2.9 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 256K context · ~273 tok/s
2.7 GB3.2 GB3-bit medium — 3-bit medium quantizationFits: 256K context · ~245 tok/s
3.2 GB3.7 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 256K context · ~205 tok/s
3.7 GB4.2 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 256K context · ~177 tok/s
4.2 GB4.7 GB6-bit, very good — 6-bit quantization, very good qualityFits: 256K context · ~156 tok/s
5.0 GB5.5 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 256K context · ~131 tok/s
9.6 GB10.1 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingFits: 256K context · ~69 tok/s
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

3.4GBat 16K context

Weights
2.7 GB
KV cache
0.3 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 20.6 GB free · ~205 tok/s

≥50 tok/s needs ≥245 GB/s · RTX 5090 ~365, M5 Ultra ~270

Which Hardware Can Run Intern Decision 4B?

Q4_K_M · 3.2 GB

Intern Decision 4B (Q4_K_M) requires 3.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 5+ GB is recommended. Using the full 262K context window can add up to 5.2 GB, bringing total usage to 8.4 GB. 114 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce GTX 1650 SUPER. 185 devices with unified memory can run Intern Decision 4B, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB), MacBook Air 13" M3 (8 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Q4_K_M · 3.4 GB · ~55 tok/s · 128K8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 3.4 GB · ~73 tok/s · 256K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 3.4 GB · ~91 tok/s · 256K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 3.4 GB · ~205 tok/s · 256K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 3.4 GB · ~26 tok/s · 256KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 3.4 GB · ~120 tok/s · 256KMacs →

Alternatives to Intern Decision 4B

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
Qwen3.5 4BAlibaba98.53.4 GB~201same size
Gemma 3 4B ITGoogle64.05 GB~231same size
Translategemma 4B ITGoogle—5 GB~231same size
Molmo2 4BAllen AI—4.7 GB~193same size
Qwen3 VL 4B InstructAlibaba—4.5 GB~208same size
Qwen3.6 27B MTPLX Optimized SpeedYoussofal—4 GB~185same size

Specifications

Publisher
InternLM
Parameters
4.5B
Architecture
Qwen3_5ForConditionalGeneration
Context Length
262,144 tokens
Vocabulary Size
248,320
Release Date
2026-09-26
License
Apache 2.0

Frequently Asked Questions

How much VRAM does Intern Decision 4B need?

Intern Decision 4B requires 3.2 GB of VRAM at Q4_K_M, or 9.6 GB at BF16. Full 262K context adds up to 5.2 GB (8.4 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 4.5B × 4.8 bits ÷ 8 = 2.7 GB

KV Cache + Overhead ≈ 0.5 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 ≈ 5.7 GB (at full 262K context)

VRAM usage by quantization

3.2 GB
8.4 GB

Learn more about VRAM estimation →

What's the best quantization for Intern Decision 4B?

For Intern Decision 4B, Q4_K_M (3.2 GB) offers the best balance of quality and VRAM usage. Q5_K_M (3.7 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 2.4 GB.

VRAM requirement by quantization

Q2_K
2.4 GB
Q4_K_M ★
3.2 GB
Q5_K_M
3.7 GB
Q6_K
4.2 GB
Q8_0
5.0 GB
BF16
9.6 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Intern Decision 4B on a Mac?

Yes — MacBook Air 13" M3 (8 GB) and 158 other Macs can run Intern Decision 4B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 3.2 GB of usable unified memory (RAM minus macOS overhead).

Can I run Intern Decision 4B locally?

Yes — Intern Decision 4B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Intern Decision 4B?

At Q4_K_M, Intern Decision 4B can reach ~1505 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~205 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 ÷ 3.19 × 0.65 = ~1630 tok/s

Estimated speed at Q4_K_M (3.2 GB)

~1630 tok/s
~205 tok/s
~1630 tok/s
~1505 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 Intern Decision 4B?

At Q4_K_M, the download is about 2.72 GB. The full-precision BF16 version is 9.08 GB. The smallest option (Q2_K) is 1.93 GB.

Which GPUs can run Intern Decision 4B?

114 consumer GPUs can run Intern Decision 4B at Q4_K_M. Top options include AMD Radeon RX 5600 XT, AMD Radeon RX 5700 XT, AMD Radeon RX 580 8GB, NVIDIA GeForce GTX 1050 Ti. 107 GPUs have plenty of headroom for comfortable inference.

Which devices can run Intern Decision 4B?

185 devices with unified memory can run Intern Decision 4B at Q4_K_M (3.2 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.