GLM 4.6V Flash — Hardware Requirements & GPU Compatibility
VisionFunctions
GLM 4.6V Flash is a 10.3B-parameter open language model from Z.ai 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.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 32K)Best on 24 GB (Q4_K_M · ~100 tok/s · 128K)Macs from 8 GB (IQ2_M · ~19 tok/s)
MIT
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run GLM 4.6V Flash
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/unsloth/GLM-4.6V-Flash-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 16.8 GB free · 16K context
Download: GLM-4.6V-Flash-Q4_K_M.gguf6.17 GBunsloth
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 (10 GB) (2 GB headroom) · Q4_K_M
- Generation speed
- ~75 tok/s
- generation speed
- Cost per 1M output tokens
- $0.40
- per 1M output tokens
How Much VRAM Does GLM 4.6V Flash Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 4.8 GB | 6 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~138 tok/s | |
| 4.9 GB | 6.2 GB | 3-bit small — 3-bit small quantization | Fits: 128K context · ~134 tok/s | |
| 5.4 GB | 6.7 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~121 tok/s | |
| 5.5 GB | 6.8 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 128K context · ~119 tok/s | |
| 6.6 GB | 7.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~100 tok/s | |
| 7.7 GB | 9 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~85 tok/s | |
| 8.9 GB | 10.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~74 tok/s | |
| 10.7 GB | 11.9 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~61 tok/s |
Selected Q4_K_M
4-bit medium quantization7.2GBat 16K context
- Weights
- 6.2 GB
- KV cache
- 0.7 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 16.9 GB free · ~100 tok/s
≥50 tok/s needs ≥504 GB/s · RTX 5090 ~178, RTX 3090 Ti ~100
Which Hardware 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. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 151 devices with unified memory can run GLM 4.6V Flash, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA Jetson Orin Nano 8GB (Super).
≤ 11 GB
≤ 11 GB tier →fits · 0.8 GB free · up to 32K ctx
16 GPUs · 1 device family
RTX 3080~75Simulate output on RTX 3080RTX 2080 Ti~61Simulate output on RTX 2080 TiRTX 3070 Ti~60Simulate output on RTX 3070 TiOrin Nano~10Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)20 GB
fits · 12.8 GB free · up to 128K ctx
1 GPU
RX 7900 XT~73Simulate output on RX 7900 XT32–40 GB
fits · 24.9 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~178Simulate output on RTX 5090M5 Max36 GB~49Simulate output on Mac Studio M5 Max (36 GB)M532 GB~16Simulate output on MacBook Air 13" M5 (32 GB)Orin~20Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~13Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to GLM 4.6V Flash
GLM 4 family · 18 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.5 9BAlibaba | 99.4 | 6.6 GB | ~103 | same size |
| SenseNova Loop 9B Previewsensenova | — | 8.2 GB | ~103 | same size |
| ZDTaichu5.0 9BTaichuAI | — | 9.2 GB | ~101 | same size |
| Ornith 1.5 9Bornith-ai | — | 6.6 GB | ~103 | same size |
| ZAYA1 VL 8BZyphra | — | 7.5 GB | ~346 | same size |
| Qwopus3.5 9B v3Jackrong | — | 6.6 GB | ~103 | same size |
Specifications
- Publisher
- Z.ai
- Family
- GLM 4
- Parameters
- 10.3B
- Architecture
- Glm4vForConditionalGeneration
- Context Length
- 131,072 tokens
- Vocabulary Size
- 151,552
- Release Date
- 2025-12-07
- License
- MIT
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)
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 ≈ 5.6 GB (at full 131K context)
VRAM usage by quantization
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
★ Recommended — best balance of quality and VRAM usage.
Can I run GLM 4.6V Flash on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run GLM 4.6V Flash, the smallest at IQ2_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 6.6 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M2 Pro (16 GB).
Can I run GLM 4.6V Flash locally?
Yes — GLM 4.6V Flash can run locally on consumer hardware. 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 ~732 tok/s on AMD Instinct MI350X. 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: NVIDIA B200 → 8000 ÷ 6.56 × 0.65 = ~793 tok/s
Estimated speed at Q4_K_M (6.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of GLM 4.6V 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?
52 consumer GPUs can run GLM 4.6V Flash at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 40 GPUs have plenty of headroom for comfortable inference.
Which devices can run GLM 4.6V Flash?
151 devices with unified memory can run GLM 4.6V Flash at Q4_K_M (6.6 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.