Can GLM 4.7 run on the RTX 4060 Ti 8GB?
Not fully in VRAM. Even at 2-bit with 8K context, GLM 4.7 needs about 126 GB, more than the 7.6 GB usable on the RTX 4060 Ti 8GB. It can still run with offload (slower): Q2_K with part of the model in system RAM, about 1.8–3.8 tokens/sec (estimate). Details and command.
Runs with offload (slower)
Runs with offload 2-bit (Q2_K) at 8K context: 4 of 92 layers on the RTX 4060 Ti 8GB (about 6.1 GB) and the other 88 in system RAM (about 120 GB). Needs a PC with at least 128 GB of system RAM. Estimated speed: 1.8–3.8 tokens/sec (slow but usable), versus a bandwidth ceiling of ~22 tok/s if it fit fully in VRAM.
llama-server -hf unsloth/GLM-4.7-GGUF:Q2_K -c 8192 -ngl 4
Estimate, not a benchmark. The command downloads the GGUF from Hugging Face. The speed range spans dual-channel DDR4-3200 to DDR5-6000 system RAM; your CPU, RAM speed and llama.cpp version move it. If llama.cpp runs out of GPU memory, lower -ngl by 2-3; if VRAM is left over, raise it for more speed. Recent llama.cpp builds can also pick the split automatically. How we estimate offload.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 124 GB No | 126 GB No | 134 GB No | 169 GB No | — |
| 3-bit (Q3_K_M) • | 162 GB No | 163 GB No | 172 GB No | 206 GB No | — |
| 4-bit (Q4_K_M) • | 204 GB No | 205 GB No | 214 GB No | 248 GB No | — |
| 5-bit (Q5_K_M) • | 239 GB No | 240 GB No | 249 GB No | 283 GB No | — |
| 6-bit (Q6_K) • | 276 GB No | 278 GB No | 286 GB No | 321 GB No | — |
| 8-bit (Q8_0) • | 357 GB No | 358 GB No | 367 GB No | 401 GB No | — |
| 16-bit (F16/BF16) • | 670 GB No | 671 GB No | 680 GB No | 714 GB No | — |
• real GGUF file size from unsloth/GLM-4.7-GGUF. Speed is a bandwidth ceiling (288 GB/s), not a benchmark. Methodology.
Hardware that does fit it
H200Mac M2 Ultra 192GBMac M3 Ultra 256GBMac M3 Ultra 512GB
What fits instead
- No listed GPU with a list price runs GLM 4.7 fully in memory. The smallest listed hardware that does is the H200 (141 GB).
- Largest popular model that fits the RTX 4060 Ti 8GB: Qwen3.5 9B (9.7B) at Q4_K_M, about 6.4 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
GLM 4.7 on every GPU and Mac · Every model that runs on the RTX 4060 Ti 8GB · Other models that fit 8 GB VRAM · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (zai-org/GLM-4.7), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.