GLM 4.6V Flash — Hardware Requirements & GPU Compatibility
Vision
GLM 4.6V Flash is a 10.3B-parameter open language model from zai-org in the GLM 4 family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 6.56 GB of VRAM — see which GPUs and Macs can run it below.
62.2K downloads
609 likesSpecifications
- Publisher
- zai-org
- Family
- GLM 4
- Parameters
- 10.3B
- Architecture
- Glm4vForConditionalGeneration
- Context Length
- 131,072 tokens
- Vocabulary Size
- 151,552
- Release Date
- 2025-12-07
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does GLM 4.6V Flash Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 4.8 GB | 10.0 GB | 4.37 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 4.9 GB | 10.2 GB | 4.50 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 5.4 GB | 10.7 GB | 5.02 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 5.5 GB | 10.8 GB | 5.15 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 6.6 GB | 11.8 GB | 6.18 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 7.7 GB | 13 GB | 7.33 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 8.9 GB | 14.2 GB | 8.49 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 10.7 GB | 16.0 GB | 10.29 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run GLM 4.6V Flash?
Q4_K_M · 6.6 GBGLM 4.6V Flash (Q4_K_M) requires 6.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 9+ GB is recommended. Using the full 131K context window can add up to 5.3 GB, bringing total usage to 11.8 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run GLM 4.6V Flash?
Q4_K_M · 6.6 GB33 devices with unified memory can run GLM 4.6V Flash, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Air 13" M3 (8 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download GLM 4.6V 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 4.6V Flash need?
GLM 4.6V Flash requires 6.6 GB of VRAM at Q4_K_M, or 21.0 GB at BF16. Full 131K context adds up to 5.3 GB (11.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 10.3B × 4.8 bits ÷ 8 = 6.2 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 5.6 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M6.6 GBQ4_K_M + full context11.8 GB- What's the best quantization for GLM 4.6V Flash?
For GLM 4.6V Flash, Q4_K_M (6.6 GB) offers the best balance of quality and VRAM usage. Q4_K_L (6.7 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 3.2 GB.
VRAM requirement by quantization
IQ2_XXS3.2 GBIQ3_XS4.6 GBQ3_K_L5.7 GBQ4_K_M ★6.6 GBQ4_K_L6.7 GBBF1621.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run GLM 4.6V Flash on a Mac?
GLM 4.6V Flash requires at least 3.2 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 4.6V Flash locally?
Yes — GLM 4.6V Flash can run locally on consumer hardware. At Q4_K_M quantization it needs 6.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is GLM 4.6V Flash?
At Q4_K_M, GLM 4.6V Flash can reach ~444 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~100 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 6.6 × 0.55 = ~444 tok/s
Estimated speed at Q4_K_M (6.6 GB)
~444 tok/s~100 tok/s~332 tok/s~275 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of GLM 4.6V Flash?
At Q4_K_M, the download is about 6.18 GB. The full-precision BF16 version is 20.59 GB. The smallest option (IQ2_XXS) is 2.83 GB.
- Which GPUs can run GLM 4.6V Flash?
35 consumer GPUs can run GLM 4.6V Flash at Q4_K_M (6.6 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 28 GPUs have plenty of headroom for comfortable inference.
- Which devices can run GLM 4.6V Flash?
33 devices with unified memory can run GLM 4.6V Flash at Q4_K_M (6.6 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.