GLM 4.7 Flash Ultimate Irrefusable Heretic — Hardware Requirements & GPU Compatibility
Chat
GLM 4.7 Flash Ultimate Irrefusable Heretic is a 29.9B-parameter open language model from llmfan46 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.
Runs great on a 24 GB GPU
Runs from 16 GB (Q3_K_M · 16K)Best on 24 GB (Q4_K_M · ~172 tok/s · 64K)Macs from 18 GB (Q2_K · ~42 tok/s)
MIT
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run GLM 4.7 Flash Ultimate Irrefusable Heretic
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve llmfan46/GLM-4.7-Flash-ultimate-irrefusable-heretic --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 3090 (24 GB) (4 GB headroom) · Q4_K_M
- Generation speed
- ~165 tok/s
- generation speed
- Cost per 1M output tokens
- $0.36
- per 1M output tokens
How Much VRAM Does GLM 4.7 Flash Ultimate Irrefusable Heretic Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 13.8 GB | 14.8 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 198K context · ~203 tok/s | |
| 15.7 GB | 16.7 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~191 tok/s | |
| 19.1 GB | 20 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 64K context · ~172 tok/s | |
| 22.4 GB | 23.4 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~157 tok/s | |
| 25.8 GB | 26.8 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 25.9 GB | |
| 31.0 GB | 32 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 31.1 GB | |
| 61.0 GB | 62 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 61.1 GB |
Selected Q4_K_M
4-bit medium quantization19.2GBat 16K context
- Weights
- 18.0 GB
- KV cache
- 0.9 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 4.9 GB free · ~172 tok/s
≥50 tok/s needs ≥187 GB/s · RTX 5090 ~227, RTX 3090 Ti ~172
Which Hardware Can Run GLM 4.7 Flash Ultimate Irrefusable Heretic?
Q4_K_M · 19.1 GBGLM 4.7 Flash Ultimate Irrefusable 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 10.2 GB, bringing total usage to 29.2 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run GLM 4.7 Flash Ultimate Irrefusable Heretic, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
fits · 0.8 GB free · up to 16K ctx
1 GPU
RX 7900 XT~72Simulate output on RX 7900 XT32–40 GB
fits · 12.8 GB free · up to 198K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~227Simulate output on RTX 5090M5 Max36 GB~63Simulate output on Mac Studio M5 Max (36 GB)M532 GB~34Simulate output on MacBook Air 13" M5 (32 GB)Orin~54Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~35Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to GLM 4.7 Flash Ultimate Irrefusable Heretic
GLM 4 family · 18 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.8 27BAlibaba | 122.1 | 17.9 GB | ~38 | same size |
| Hy Memory 30B A3BTencent | — | 19.1 GB | ~184 | same size |
| Llm Jp 4.1 32B A3b Thinkingllm-jp | — | 20.1 GB | ~188 | same size |
| Muse Glimmer 30BMeta | — | 19.6 GB | ~36 | same size |
| NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA | — | 19.3 GB | ~197 | same size |
| Hy MT2 30B A3BTencent | — | 19.1 GB | ~170 | same size |
Specifications
- Publisher
- llmfan46
- Family
- GLM 4
- Parameters
- 29.9B
- Active parameters
- 3.3B per token
- Architecture
- Glm4MoeLiteForCausalLM
- Context Length
- 202,752 tokens
- Vocabulary Size
- 154,880
- Release Date
- 2026-03-11
- License
- MIT
Frequently Asked Questions
How much VRAM does GLM 4.7 Flash Ultimate Irrefusable Heretic need?
GLM 4.7 Flash Ultimate Irrefusable Heretic requires 19.1 GB of VRAM at Q4_K_M, or 61.0 GB at BF16. Full 203K context adds up to 10.2 GB (29.2 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)
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 ≈ 11.2 GB (at full 203K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run GLM 4.7 Flash Ultimate Irrefusable 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 Ultimate Irrefusable Heretic?
For GLM 4.7 Flash Ultimate Irrefusable 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
★ Recommended — best balance of quality and VRAM usage.
Can I run GLM 4.7 Flash Ultimate Irrefusable Heretic on a Mac?
Yes — MacBook Pro 14" M3 Pro (18 GB) and 108 other Macs can run GLM 4.7 Flash Ultimate Irrefusable Heretic, the smallest at Q2_K. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 19.1 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).
Can I run GLM 4.7 Flash Ultimate Irrefusable Heretic locally?
Yes — GLM 4.7 Flash Ultimate Irrefusable Heretic can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is GLM 4.7 Flash Ultimate Irrefusable Heretic?
At Q4_K_M, GLM 4.7 Flash Ultimate Irrefusable 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 = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 2.1 GB active ÷ (8000 × 0.65) = 0.41 ms, plus 47 layers × 0.055 ms = 2.58 ms, so 1000 ÷ 2.99 ms = ~334 tok/s
Estimated speed at Q4_K_M (19.1 GB)
Real-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 Ultimate Irrefusable 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 Ultimate Irrefusable Heretic?
8 consumer GPUs can run GLM 4.7 Flash Ultimate Irrefusable Heretic at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run GLM 4.7 Flash Ultimate Irrefusable Heretic?
122 devices with unified memory can run GLM 4.7 Flash Ultimate Irrefusable Heretic at Q4_K_M (19.1 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.