GLM 4.7 Flash — Hardware Requirements & GPU Compatibility
Chat
GLM 4.7 Flash is a 31.2B-parameter open language model from Z.ai in the GLM 4 family. It supports a context window of up to 202,752 tokens. At Q4_K_M it needs about 19.82 GB of VRAM — see which GPUs and Macs can run it below.
2.3M downloads
1.8K likesSpecifications
- Publisher
- Z.ai
- Family
- GLM 4
- Parameters
- 31.2B
- Architecture
- Glm4MoeLiteForCausalLM
- Context Length
- 202,752 tokens
- Vocabulary Size
- 154,880
- Release Date
- 2026-01-19
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does GLM 4.7 Flash Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 14.4 GB | 91.6 GB | 13.27 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 14.8 GB | 92.0 GB | 13.66 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 16.3 GB | 93.6 GB | 15.22 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 16.7 GB | 94.0 GB | 15.61 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 19.8 GB | 97.1 GB | 18.73 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 23.3 GB | 100.6 GB | 22.25 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 26.9 GB | 104.1 GB | 25.76 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 32.3 GB | 109.6 GB | 31.22 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run GLM 4.7 Flash?
Q4_K_M · 19.8 GBGLM 4.7 Flash (Q4_K_M) requires 19.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 26+ GB is recommended. Using the full 203K context window can add up to 77.3 GB, bringing total usage to 97.1 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run GLM 4.7 Flash?
Q4_K_M · 19.8 GB41 devices with unified memory can run GLM 4.7 Flash, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download GLM 4.7 Flash
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 4.7 Flash need?
GLM 4.7 Flash requires 19.8 GB of VRAM at Q4_K_M, or 63.5 GB at BF16. Full 203K context adds up to 77.3 GB (97.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 31.2B × 4.8 bits ÷ 8 = 18.7 GB
KV Cache + Overhead ≈ 1.1 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 78.4 GB (at full 203K context)
VRAM usage by quantization
Q4_K_M19.8 GBQ4_K_M + full context97.1 GB- Can NVIDIA GeForce RTX 4090 run GLM 4.7 Flash?
Yes, at Q5_K_M (23.3 GB) or lower. Higher quantizations like Q6_K (26.9 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for GLM 4.7 Flash?
For GLM 4.7 Flash, Q4_K_M (19.8 GB) offers the best balance of quality and VRAM usage. Q5_K_S (22.6 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 9.7 GB.
VRAM requirement by quantization
IQ2_XXS9.7 GBQ3_K_S14.8 GBQ4_118.6 GBQ4_K_M ★19.8 GBQ5_K_S22.6 GBBF1663.5 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run GLM 4.7 Flash on a Mac?
GLM 4.7 Flash requires at least 9.7 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 4.7 Flash locally?
Yes — GLM 4.7 Flash can run locally on consumer hardware. At Q4_K_M quantization it needs 19.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is GLM 4.7 Flash?
At Q4_K_M, GLM 4.7 Flash can reach ~222 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~33 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 ÷ 19.8 × 0.65 = ~262 tok/s
Estimated speed at Q4_K_M (19.8 GB)
~262 tok/s~33 tok/s~262 tok/s~222 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of GLM 4.7 Flash?
At Q4_K_M, the download is about 18.73 GB. The full-precision BF16 version is 62.44 GB. The smallest option (IQ2_XXS) is 8.59 GB.
- Which GPUs can run GLM 4.7 Flash?
8 consumer GPUs can run GLM 4.7 Flash at Q4_K_M (19.8 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run GLM 4.7 Flash?
41 devices with unified memory can run GLM 4.7 Flash at Q4_K_M (19.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (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.