readygpu

GLM 4.6V Flash

10.3B parameters · 128k context · MIT · released 2025-12-07

visionagenticcodingreasoningchat

In short

GLM 4.6V Flash is an open model from Z.ai with 10.3B parameters. At Q4_K_M, GLM 4.6V Flash needs about 7 GB of memory at 8k context and 9 GB at 64k, counting the weights, the KV cache and runtime buffers. The cheapest hardware in Canada that runs GLM 4.6V Flash fully in memory at 64k context is the NVIDIA GeForce RTX 3060 12GB, $497 at Amazon, at about 25 tok/s (estimated).

Updated . Speeds are estimates; how they are worked out.

What to run it on in Canada

Fully in memory at 64k context, priced at retailers today.

All hardware that runs it

Everything we price, best value first. Two cards split the model by layers.

HardwareQuantFitsDecodePricetok/s per 1,000
NVIDIA GeForce RTX 3060 12GBQ4_K_Mfits25 tok/s$49750.7
Intel Arc B580Q4_K_Mfits26 tok/s$56046.1
Intel Arc A770 16GBQ8_0fits22 tok/s$65533.7
NVIDIA GeForce RTX 3080 10GBQ4_K_Mfits53 tok/s$76969.2
AMD Radeon RX 9060 XT 16GBQ8_0fits14 tok/s$80017.4
AMD Radeon RX 9070 XTQ8_0fits28 tok/s$1,05026.5
Intel Arc Pro B60Q8_0fits18 tok/s$1,06017.0
NVIDIA GeForce RTX 5060 Ti 16GBQ8_0fits22 tok/s$1,12019.6
NVIDIA GeForce RTX 5070Q4_K_Mfits47 tok/s$1,18139.9
AMD Radeon RX 7800 XTQ8_0fits27 tok/s$1,39719.4
Mac mini M4 16GBQ4_K_Mfits9 tok/s$1,3996.3
NVIDIA GeForce RTX 4070 SuperQ4_K_Mfits35 tok/s$1,40025.2
AMD Radeon RX 7600 XTQ8_0fits13 tok/s$1,4408.7
NVIDIA GeForce RTX 5070 TiQ8_0fits44 tok/s$1,69025.9
NVIDIA GeForce RTX 4070 Ti SuperQ8_0fits33 tok/s$1,79018.3
NVIDIA GeForce RTX 4080 SuperQ8_0fits36 tok/s$2,00018.0
AMD Radeon RX 7900 XTQ8_0fits35 tok/s$2,08316.7
NVIDIA GeForce RTX 5080Q8_0fits47 tok/s$2,37019.8
NVIDIA GeForce RTX 3090Q8_0fits46 tok/s$2,80016.4
AMD Radeon AI PRO R9700Q8_0fits28 tok/s$2,8009.9
NVIDIA RTX PRO 6000 BlackwellQ8_0fits88 tok/s$3,13328.0
NVIDIA GeForce RTX 3090 TiQ8_0fits49 tok/s$3,99912.3
GMKtec EVO-X2 Ryzen AI Max+ 395 128GBQ8_0fits11 tok/s$5,0992.2
NVIDIA GeForce RTX 4090Q8_0fits49 tok/s$7,1076.9
ASUS Ascent GX10 128GBQ8_0fits13 tok/s$8,2991.6
NVIDIA GeForce RTX 5090Q8_0fits88 tok/s$10,3008.5
Mac Studio M4 Max 128GBQ8_0fits28 tok/s––
Mac mini M4 Pro 64GBQ8_0fits14 tok/s––
AMD Radeon RX 7900 XTXQ8_0fits42 tok/s––
Framework Desktop Ryzen AI Max+ 395 128GBQ8_0fits11 tok/s––
Mac Studio M3 Ultra 512GBQ8_0fits42 tok/s––
NVIDIA DGX Spark 128GBQ8_0fits13 tok/s––
Mac Studio M3 Ultra 256GBQ8_0fits42 tok/s––
Mac mini M4 Pro 48GBQ8_0fits14 tok/s––
NVIDIA GeForce RTX 4060 Ti 16GBQ8_0fits14 tok/s––
Mac Studio M4 Max 64GBQ8_0fits28 tok/s––
Mac Studio M3 Ultra 96GBQ8_0fits42 tok/s––
Framework Desktop Ryzen AI Max+ 395 64GBQ8_0fits11 tok/s––
Mac mini M4 32GBQ8_0fits6 tok/s––
NVIDIA Tesla P40Q8_0fits17 tok/s––

Memory needed

Weights, KV cache and runtime buffers at each context length (KV cache at fp16).

QuantFile@8k@32k@64k@128k
Q4_K_Mgguf5.7 GB6.8 GB7.9 GB9.3 GB12.2 GB
Q8_0gguf9.3 GB10.4 GB11.5 GB12.9 GB15.8 GB

Run it

Copy a command for the runtime you use.

  • Q4_K_M
    • Ollamaollama run hf.co/ggml-org/GLM-4.6V-Flash-GGUF:Q4_K_M
    • LM Studiolms get ggml-org/GLM-4.6V-Flash-GGUF@q4_k_m
    • llama.cppllama-server -hf ggml-org/GLM-4.6V-Flash-GGUF:Q4_K_M
  • Q8_0
    • Ollamaollama run hf.co/ggml-org/GLM-4.6V-Flash-GGUF:Q8_0
    • LM Studiolms get ggml-org/GLM-4.6V-Flash-GGUF@q8_0
    • llama.cppllama-server -hf ggml-org/GLM-4.6V-Flash-GGUF:Q8_0

Notes

This repo hosts GLM-4.6V-Flash (9B), the lightweight variant, not the 106B GLM-4.6V; vLLM serving needs vllm>=0.12.0 and transformers>=5.0.0rc0 (SGLang needs >=0.5.6.post1). The card admits that pure-text QA is weak and that the model can overthink or repeat itself.

Questions

How much VRAM does GLM 4.6V Flash need?
At Q4_K_M, GLM 4.6V Flash needs about 7 GB of memory at 8k context and 9 GB at 64k, counting the weights, the KV cache and runtime buffers.
What is the best GPU for running GLM 4.6V Flash locally?
The cheapest hardware in Canada that runs GLM 4.6V Flash fully in memory at 64k context is the NVIDIA GeForce RTX 3060 12GB, $497 at Amazon, at about 25 tok/s (estimated). The best value is the NVIDIA GeForce RTX 3080 10GB (about 53 tok/s for $769). The fastest we price is the NVIDIA RTX PRO 6000 Blackwell, at about 88 tok/s.
Can I run GLM 4.6V Flash on a 16 GB GPU?
Yes: at Q8_0 it fits fully in 16 GB at 64k context. On the NVIDIA GeForce RTX 5080 it runs at about 47 tok/s (estimated).
Can I run GLM 4.6V Flash on a 24 GB GPU?
Yes: at Q8_0 it fits fully in 24 GB at 64k context. On the NVIDIA GeForce RTX 3090 Ti it runs at about 49 tok/s (estimated).
How do I run GLM 4.6V Flash locally?
With Ollama: ollama run hf.co/ggml-org/GLM-4.6V-Flash-GGUF:Q4_K_M (the Q4_K_M build). LM Studio and llama.cpp commands are on this page.
What licence is GLM 4.6V Flash released under?
MIT, which allows commercial use.