GLM 4.7 Flash Heretic — Hardware Requirements & GPU Compatibility
Chat
GLM 4.7 Flash Heretic is a 29.9B-parameter open language model from Olafangensan in the GLM 4 family. It supports a context window of up to 202,752 tokens. At Q4_K_M it needs about 19.05 GB of VRAM — see which GPUs and Macs can run it below.
1.1K downloads
24 likesSpecifications
- Publisher
- Olafangensan
- Family
- GLM 4
- Parameters
- 29.9B
- Architecture
- Glm4MoeLiteForCausalLM
- Context Length
- 202,752 tokens
- Vocabulary Size
- 154,880
- Release Date
- 2026-01-21
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does GLM 4.7 Flash Heretic Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 13.8 GB | 91.1 GB | 12.73 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 15.7 GB | 93.0 GB | 14.60 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 19.1 GB | 96.3 GB | 17.97 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 22.4 GB | 99.7 GB | 21.33 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 25.8 GB | 103.1 GB | 24.70 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 31.0 GB | 108.3 GB | 29.94 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 61.0 GB | 138.3 GB | 59.89 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 GLM 4.7 Flash Heretic?
Q4_K_M · 19.1 GBGLM 4.7 Flash Heretic (Q4_K_M) requires 19.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 25+ GB is recommended. Using the full 203K context window can add up to 77.3 GB, bringing total usage to 96.3 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 Heretic?
Q4_K_M · 19.1 GB41 devices with unified memory can run GLM 4.7 Flash Heretic, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does GLM 4.7 Flash Heretic need?
GLM 4.7 Flash Heretic requires 19.1 GB of VRAM at Q4_K_M, or 61.0 GB at BF16. Full 203K context adds up to 77.3 GB (96.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 29.9B × 4.8 bits ÷ 8 = 18 GB
KV Cache + Overhead ≈ 1.1 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 78.3 GB (at full 203K context)
VRAM usage by quantization
Q4_K_M19.1 GBQ4_K_M + full context96.3 GB- Can NVIDIA GeForce RTX 4090 run GLM 4.7 Flash Heretic?
Yes, at Q5_K_M (22.4 GB) or lower. Higher quantizations like Q6_K (25.8 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for GLM 4.7 Flash Heretic?
For GLM 4.7 Flash Heretic, Q4_K_M (19.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (22.4 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 13.8 GB.
VRAM requirement by quantization
Q2_K13.8 GBQ4_K_M ★19.1 GBQ5_K_M22.4 GBQ6_K25.8 GBQ8_031.0 GBBF1661.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run GLM 4.7 Flash Heretic on a Mac?
GLM 4.7 Flash Heretic requires at least 13.8 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 GLM 4.7 Flash Heretic locally?
Yes — GLM 4.7 Flash Heretic can run locally on consumer hardware. At Q4_K_M quantization it needs 19.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is GLM 4.7 Flash Heretic?
At Q4_K_M, GLM 4.7 Flash Heretic can reach ~102 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~172 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 ÷ 19.1 × 0.65 = ~334 tok/s
Estimated speed at Q4_K_M (19.1 GB)
~334 tok/s~172 tok/s~334 tok/s~308 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 Heretic?
At Q4_K_M, the download is about 17.97 GB. The full-precision BF16 version is 59.89 GB. The smallest option (Q2_K) is 12.73 GB.
- Which GPUs can run GLM 4.7 Flash Heretic?
8 consumer GPUs can run GLM 4.7 Flash Heretic at Q4_K_M (19.1 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 Heretic?
41 devices with unified memory can run GLM 4.7 Flash Heretic at Q4_K_M (19.1 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.