GLM 5.3 DFlash2 — Hardware Requirements & GPU Compatibility
Chat
GLM 5.3 DFlash2 is a 2.5B-parameter open language model from incoai in the GLM 5 family. It supports a context window of up to 1,048,576 tokens. At Q4_K_M it needs about 1.81 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 256K)Best on 24 GB (Q4_K_M · ~362 tok/s · 1M)Macs from 8 GB (Q4_K_M · ~40 tok/s)
cc-by-nc-nd-4.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run GLM 5.3 DFlash2
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve incoai/GLM-5.3-DFlash2 --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (9 GB headroom) · Q4_K_M
- Generation speed
- ~129 tok/s
- generation speed
- Cost per 1M output tokens
- $0.18
- per 1M output tokens
How Much VRAM Does GLM 5.3 DFlash2 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.4 GB | 2 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 1M context · ~475 tok/s | |
| 1.5 GB | 2.1 GB | 3-bit medium — 3-bit medium quantization | Fits: 1M context · ~426 tok/s | |
| 1.8 GB | 2.4 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 1M context · ~362 tok/s | |
| 2.1 GB | 2.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 1M context · ~314 tok/s | |
| 2.4 GB | 2.9 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 1M context · ~277 tok/s | |
| 2.8 GB | 3.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 1M context · ~234 tok/s | |
| 5.3 GB | 5.8 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 512K context · ~125 tok/s |
Selected Q4_K_M
4-bit medium quantization2.1GBat 16K context
- Weights
- 1.5 GB
- KV cache
- 0.3 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.9 GB free · ~362 tok/s
≥50 tok/s needs ≥139 GB/s · RTX 5090 ~644, RTX 3090 Ti ~362
Which Hardware Can Run GLM 5.3 DFlash2?
Q4_K_M · 1.8 GBGLM 5.3 DFlash2 (Q4_K_M) requires 1.8 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 1049K context window can add up to 19.3 GB, bringing total usage to 21.1 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run GLM 5.3 DFlash2, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.9 GB free · up to 256K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~273Simulate output on RTX 3080RTX 2080 Ti~221Simulate output on RTX 2080 TiRTX 3070 Ti~219Simulate output on RTX 3070 TiM3*8 GB~40Simulate output on iMac 24" M3 (8 GB)Orin Nano~37Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~26Simulate output on iPhone 1720 GB
fits · 17.9 GB free · up to 512K ctx
1 GPU
RX 7900 XT~265Simulate output on RX 7900 XT32–40 GB
fits · 29.9 GB free · up to 1M ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~644Simulate output on RTX 5090M5 Max36 GB~178Simulate output on Mac Studio M5 Max (36 GB)M532 GB~59Simulate output on MacBook Air 13" M5 (32 GB)Orin~74Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~49Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to GLM 5.3 DFlash2
GLM 5 family · 6 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM5 2BOpenBMB | — | 2.5 GB | ~345 | same size |
| North Micro Vision InstructCohere | — | 7.1 GB | ~119 | same size |
| Granite 3.1 2B InstructIBM | — | 3.2 GB | ~329 | same size |
| Gemma 2 2B ITGoogle | — | 2.5 GB | ~379 | same size |
| EXAONE 3.5 2.4B InstructLGAI-EXAONE | — | 3.4 GB | ~412 | same size |
| Sarvam 1sarvamai | — | 2.8 GB | ~320 | same size |
Specifications
- Publisher
- incoai
- Family
- GLM 5
- Parameters
- 2.5B
- Architecture
- DFlash2DraftModel
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 154,880
- Release Date
- 2026-08-26
- License
- cc-by-nc-nd-4.0
Frequently Asked Questions
How much VRAM does GLM 5.3 DFlash2 need?
GLM 5.3 DFlash2 requires 1.8 GB of VRAM at Q4_K_M, or 5.3 GB at BF16. Full 1049K context adds up to 19.3 GB (21.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 2.5B × 4.8 bits ÷ 8 = 1.5 GB
KV Cache + Overhead ≈ 0.3 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 ≈ 19.6 GB (at full 1049K context)
VRAM usage by quantization
What's the best quantization for GLM 5.3 DFlash2?
For GLM 5.3 DFlash2, Q4_K_M (1.8 GB) offers the best balance of quality and VRAM usage. Q5_K_M (2.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run GLM 5.3 DFlash2 on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run GLM 5.3 DFlash2. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run GLM 5.3 DFlash2 locally?
Yes — GLM 5.3 DFlash2 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is GLM 5.3 DFlash2?
At Q4_K_M, GLM 5.3 DFlash2 can reach ~2652 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~362 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 ÷ 1.81 × 0.65 = ~2873 tok/s
Estimated speed at Q4_K_M (1.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of GLM 5.3 DFlash2?
At Q4_K_M, the download is about 1.48 GB. The full-precision BF16 version is 4.92 GB. The smallest option (Q2_K) is 1.05 GB.
Which GPUs can run GLM 5.3 DFlash2?
52 consumer GPUs can run GLM 5.3 DFlash2 at Q4_K_M. 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 GLM 5.3 DFlash2?
163 devices with unified memory can run GLM 5.3 DFlash2 at Q4_K_M (1.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.