llmrun
InternLMQwen3_5ForConditionalGeneration

Intern Decision 2B — Hardware Requirements & GPU Compatibility

VisionFunctions

Intern-Decision-2B is InternLM's 2.2-billion-parameter multimodal structured decision model, fine-tuned from Qwen3.5-2B. Instead of generating free-form text, it accepts a shared state, a schema of named questions with optional images, and returns an answer distribution for each question in one forward pass by scoring candidate option symbols. The card shows average scores of 84.68 on decision benchmarks and roughly 33 ms per query using a single RTX 4090 GPU. At this scale, it runs easily on modest consumer hardware. The model handles context windows up to 262,144 tokens. Released under the Apache 2.0 license, it allows unrestricted commercial and research use and appeared in September 2026. Positioned between the 0.8B and 4B models within the Intern-Decision family, using it requires the custom inference code provided with the repository instead of a standard chat interface.

2.2B params · dense262K contextApache 2.01.9K downloads19 likes927 quant downloads
Based on Qwen3.5 2B
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 256KBest on24 GB Q4_K_M · ~379 tok/s · 256KMacs from8 GB Q4_K_M · ~41 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Intern Decision 2B

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/bombdefuser-124/Intern-Decision-2B-GGUF

Q4_K_M fits fully on the RTX 4090 · 22.2 GB free · 16K context

Download: Intern-Decision-2B-Q4_K_M.gguf1.33 GBbombdefuser-124

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Runs on RTX 3060 12GB (10 GB headroom) · Q4_K_M

Generation speed
~135 tok/s
generation speed
Cost per 1M output tokens
$0.13
per 1M output tokens

How Much VRAM Does Intern Decision 2B Need?

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

QuantizationVRAM+32KOn RTX 4090 (reference)
1.3 GB1.6 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 256K context · ~489 tok/s
1.5 GB1.8 GB3-bit medium — 3-bit medium quantizationFits: 256K context · ~443 tok/s
1.7 GB2 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 256K context · ~379 tok/s
2.0 GB2.3 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 256K context · ~331 tok/s
2.2 GB2.5 GB6-bit, very good — 6-bit quantization, very good qualityFits: 256K context · ~294 tok/s
2.6 GB2.9 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 256K context · ~251 tok/s
4.8 GB5.1 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingFits: 256K context · ~136 tok/s
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

1.8GBat 16K context

Weights
1.3 GB
KV cache
0.2 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 22.2 GB free · ~379 tok/s

≥50 tok/s needs ≥133 GB/s · RTX 5090 ~673, M5 Ultra ~497

Which Hardware Can Run Intern Decision 2B?

Q4_K_M · 1.7 GB

Intern Decision 2B (Q4_K_M) requires 1.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 262K context window can add up to 3.1 GB, bringing total usage to 4.8 GB. 114 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 185 devices with unified memory can run Intern Decision 2B, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Q4_K_M · 1.8 GB · ~102 tok/s · 256K8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 1.8 GB · ~135 tok/s · 256K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 1.8 GB · ~168 tok/s · 256K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 1.8 GB · ~379 tok/s · 256K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 1.8 GB · ~49 tok/s · 256KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 1.8 GB · ~221 tok/s · 256KMacs →

Alternatives to Intern Decision 2B

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
LFM3 Omni 2BLiquid AI—2.4 GB~385same size
Qwen3.5 2BAlibaba—1.9 GB~370same size
Qwen3 VL 2B InstructAlibaba—3.5 GB~362same size
Qwen2 VL 2B InstructAlibaba—2.1 GB~390same size
Kimi K3 DSparkRadixArk—2.2 GB~381same size
Gemma 4 31B IT Speculator.eagle3RedHatAI—5 GB~205same size

Specifications

Publisher
InternLM
Parameters
2.2B
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 2B need?

Intern Decision 2B requires 1.7 GB of VRAM at Q4_K_M, or 4.8 GB at BF16. Full 262K context adds up to 3.1 GB (4.8 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 2.2B × 4.8 bits ÷ 8 = 1.3 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 ≈ 3.6 GB (at full 262K context)

VRAM usage by quantization

1.7 GB
4.8 GB

Learn more about VRAM estimation →

What's the best quantization for Intern Decision 2B?

For Intern Decision 2B, Q4_K_M (1.7 GB) offers the best balance of quality and VRAM usage. Q5_K_M (2.0 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.3 GB.

VRAM requirement by quantization

Q2_K
1.3 GB
Q4_K_M ★
1.7 GB
Q5_K_M
2.0 GB
Q6_K
2.2 GB
Q8_0
2.6 GB
BF16
4.8 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Intern Decision 2B on a Mac?

Yes — Mac Mini M2 (8 GB) and 158 other Macs can run Intern Decision 2B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.7 GB of usable unified memory (RAM minus macOS overhead).

Can I run Intern Decision 2B locally?

Yes — Intern Decision 2B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Intern Decision 2B?

At Q4_K_M, Intern Decision 2B can reach ~2775 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~379 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 ÷ 1.73 × 0.65 = ~3006 tok/s

Estimated speed at Q4_K_M (1.7 GB)

~3006 tok/s
~379 tok/s
~3006 tok/s
~2775 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 2B?

At Q4_K_M, the download is about 1.33 GB. The full-precision BF16 version is 4.43 GB. The smallest option (Q2_K) is 0.94 GB.

Which GPUs can run Intern Decision 2B?

114 consumer GPUs can run Intern Decision 2B 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 Intern Decision 2B?

185 devices with unified memory can run Intern Decision 2B at Q4_K_M (1.7 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.