Intern Decision 2B — Hardware Requirements & GPU Compatibility
Vision
Intern-Decision-2B is InternLM's 2.2-billion-parameter multimodal structured decision model, fine-tuned from Qwen3.5-2B. Rather than generating free-form text, it takes a shared state, a schema of named questions and optional images, and returns an answer distribution for every question in a single forward pass by scoring candidate option symbols. The card reports an average of 84.68 across its decision benchmarks and about 33 ms per query on a single RTX 4090. At this size it runs easily on a modest consumer GPU. 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 sits between the 0.8B and 4B models in the Intern-Decision family, and its use requires the custom inference code shipped with the repository rather than a standard chat interface.
575 downloads
15 likesSpecifications
- 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
Get Started
HuggingFace
How Much VRAM Does Intern Decision 2B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 1.3 GB | 14.1 GB | 0.94 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 1.5 GB | 14.3 GB | 1.08 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 1.7 GB | 14.5 GB | 1.33 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 2.0 GB | 14.8 GB | 1.58 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 2.2 GB | 15.0 GB | 1.83 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 2.6 GB | 15.4 GB | 2.21 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 4.8 GB | 17.6 GB | 4.43 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Intern Decision 2B?
Q4_K_M · 1.7 GBIntern 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 12.8 GB, bringing total usage to 14.5 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Intern Decision 2B?
Q4_K_M · 1.7 GB59 devices with unified memory can run Intern Decision 2B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download Intern Decision 2B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
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 12.8 GB (14.5 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)
KV Cache + Overhead ≈ 13.2 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M1.7 GBQ4_K_M + full context14.5 GB- 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_K1.3 GBQ4_K_M ★1.7 GBQ5_K_M2.0 GBQ6_K2.2 GBQ8_02.6 GBBF164.8 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Intern Decision 2B on a Mac?
Intern Decision 2B requires at least 1.3 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Intern Decision 2B locally?
Yes — Intern Decision 2B can run locally on consumer hardware. At Q4_K_M quantization it needs 1.7 GB of VRAM. 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 ÷ 1.7 × 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/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- 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?
52 consumer GPUs can run Intern Decision 2B at Q4_K_M (1.7 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Intern Decision 2B?
59 devices with unified memory can run Intern Decision 2B at Q4_K_M (1.7 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.