GLM 4.5 Air REAP 82B A12B — Hardware Requirements & GPU Compatibility
Chat
GLM 4.5 Air REAP 82B A12B is a 81.9B-parameter open language model from Cerebras in the GLM 4 family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 49.59 GB of VRAM — see which GPUs and Macs can run it below.
211 downloads
115 likesSpecifications
- Publisher
- Cerebras
- Family
- GLM 4
- Parameters
- 81.9B
- Architecture
- Glm4MoeForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 151,552
- Release Date
- 2025-10-20
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does GLM 4.5 Air REAP 82B A12B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 35.3 GB | 43.4 GB | 34.82 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 36.3 GB | 44.4 GB | 35.85 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 40.4 GB | 48.5 GB | 39.94 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 41.4 GB | 49.5 GB | 40.97 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 49.6 GB | 57.7 GB | 49.16 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 58.8 GB | 66.9 GB | 58.38 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 68.0 GB | 76.1 GB | 67.59 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 82.4 GB | 90.5 GB | 81.93 GB | 8-bit quantization, near-lossless |
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 GLM 4.5 Air REAP 82B A12B?
Q4_K_M · 49.6 GBGLM 4.5 Air REAP 82B A12B (Q4_K_M) requires 49.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 65+ GB is recommended. Using the full 131K context window can add up to 8.1 GB, bringing total usage to 57.7 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run GLM 4.5 Air REAP 82B A12B?
Q4_K_M · 49.6 GB22 devices with unified memory can run GLM 4.5 Air REAP 82B A12B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio (M3 Ultra, 96GB).
Runs great
— Plenty of headroom
Where to Download GLM 4.5 Air REAP 82B A12B
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 GLM 4.5 Air REAP 82B A12B need?
GLM 4.5 Air REAP 82B A12B requires 49.6 GB of VRAM at Q4_K_M, or 164.3 GB at BF16. Full 131K context adds up to 8.1 GB (57.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 81.9B × 4.8 bits ÷ 8 = 49.2 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 8.5 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M49.6 GBQ4_K_M + full context57.7 GB- Can NVIDIA GeForce RTX 4090 run GLM 4.5 Air REAP 82B A12B?
Yes, at IQ2_XXS (23.0 GB) or lower. Higher quantizations like IQ2_XS (25.0 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for GLM 4.5 Air REAP 82B A12B?
For GLM 4.5 Air REAP 82B A12B, Q4_K_M (49.6 GB) offers the best balance of quality and VRAM usage. Q4_K_L (50.6 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 23.0 GB.
VRAM requirement by quantization
IQ2_XXS23.0 GBQ2_K35.3 GBQ3_K_L42.4 GBQ4_K_M ★49.6 GBQ4_K_L50.6 GBBF16164.3 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run GLM 4.5 Air REAP 82B A12B on a Mac?
GLM 4.5 Air REAP 82B A12B requires at least 23.0 GB at IQ2_XXS, 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 GLM 4.5 Air REAP 82B A12B locally?
Yes — GLM 4.5 Air REAP 82B A12B can run locally on consumer hardware. At Q4_K_M quantization it needs 49.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is GLM 4.5 Air REAP 82B A12B?
At Q4_K_M, GLM 4.5 Air REAP 82B A12B can reach ~97 tok/s on AMD Instinct MI350X. 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 ÷ 49.6 × 0.65 = ~105 tok/s
Estimated speed at Q4_K_M (49.6 GB)
~105 tok/s~105 tok/s~97 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of GLM 4.5 Air REAP 82B A12B?
At Q4_K_M, the download is about 49.16 GB. The full-precision BF16 version is 163.86 GB. The smallest option (IQ2_XXS) is 22.53 GB.
- Which GPUs can run GLM 4.5 Air REAP 82B A12B?
No single consumer GPU has enough VRAM to run GLM 4.5 Air REAP 82B A12B at Q4_K_M (49.6 GB). Multi-GPU or professional hardware is required.
- Which devices can run GLM 4.5 Air REAP 82B A12B?
23 devices with unified memory can run GLM 4.5 Air REAP 82B A12B at Q4_K_M (49.6 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), 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.