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 7 GB at 8k, counting the weights, the KV cache and runtime buffers. The cheapest hardware in Germany that runs GLM 4.6V Flash fully in memory at 8k context is the NVIDIA GeForce RTX 3060 12GB, 309 € at Amazon, at about 22 tok/s (estimated).

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

What to run it on in Germany

Fully in memory at 8k 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 12GBQ8_0fits22 tok/s309 €69.9
Intel Arc B580Q8_0fits22 tok/s360 €61.5
NVIDIA Tesla P40Q8_0fits21 tok/s369 €56.4
NVIDIA GeForce RTX 3080 10GBQ4_K_Mfits73 tok/s500 €145.0
AMD Radeon RX 9060 XT 16GBQ8_0fits17 tok/s550 €30.9
Intel Arc A770 16GBQ8_0fits27 tok/s646 €42.0
NVIDIA GeForce RTX 4060 Ti 16GBQ8_0fits17 tok/s650 €26.6
NVIDIA GeForce RTX 5070Q8_0fits40 tok/s699 €57.7
NVIDIA GeForce RTX 4070 SuperQ8_0fits30 tok/s707 €42.7
NVIDIA GeForce RTX 5060 Ti 16GBQ8_0fits27 tok/s739 €36.4
AMD Radeon RX 9070 XTQ8_0fits34 tok/s778 €43.8
Mac mini M4 16GBQ8_0fits8 tok/s800 €9.4
AMD Radeon RX 7600 XTQ8_0fits15 tok/s813 €18.8
AMD Radeon RX 7900 XTQ8_0fits43 tok/s855 €49.8
AMD Radeon RX 7800 XTQ8_0fits33 tok/s1.002 €33.1
Intel Arc Pro B60Q8_0fits22 tok/s1.074 €20.6
NVIDIA GeForce RTX 4080 SuperQ8_0fits44 tok/s1.100 €40.2
NVIDIA GeForce RTX 5070 TiQ8_0fits54 tok/s1.149 €46.8
NVIDIA GeForce RTX 4070 Ti SuperQ8_0fits40 tok/s1.247 €32.3
Mac mini M4 32GBQ8_0fits8 tok/s1.400 €5.4
NVIDIA GeForce RTX 5080Q8_0fits58 tok/s1.500 €38.4
AMD Radeon RX 7900 XTXQ8_0fits51 tok/s1.555 €32.9
NVIDIA GeForce RTX 3090Q8_0fits56 tok/s1.850 €30.4
AMD Radeon AI PRO R9700Q8_0fits34 tok/s1.867 €18.3
NVIDIA GeForce RTX 3090 TiQ8_0fits61 tok/s2.500 €24.2
Mac mini M4 Pro 48GBQ8_0fits17 tok/s2.699 €6.4
Mac mini M4 Pro 64GBQ8_0fits17 tok/s2.799 €6.1
GMKtec EVO-X2 Ryzen AI Max+ 395 128GBQ8_0fits14 tok/s3.700 €3.7
NVIDIA GeForce RTX 4090Q8_0fits61 tok/s3.955 €15.3
Mac Studio M4 Max 64GBQ8_0fits34 tok/s4.183 €8.2
Mac Studio M4 Max 128GBQ8_0fits34 tok/s5.800 €5.9
Mac Studio M3 Ultra 96GBQ8_0fits52 tok/s5.999 €8.6
NVIDIA GeForce RTX 5090Q8_0fits108 tok/s6.028 €17.8
NVIDIA DGX Spark 128GBQ8_0fits16 tok/s8.313 €2.0
ASUS Ascent GX10 128GBQ8_0fits16 tok/s8.623 €1.9
Mac Studio M3 Ultra 256GBQ8_0fits52 tok/s15.555 €3.3
Mac Studio M3 Ultra 512GBQ8_0fits52 tok/s18.995 €2.7
NVIDIA RTX PRO 6000 BlackwellQ8_0fits108 tok/s19.076 €5.6
Framework Desktop Ryzen AI Max+ 395 128GBQ8_0fits14 tok/s––
Framework Desktop Ryzen AI Max+ 395 64GBQ8_0fits14 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 7 GB at 8k, 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 Germany that runs GLM 4.6V Flash fully in memory at 8k context is the NVIDIA GeForce RTX 3060 12GB, 309 € at Amazon, at about 22 tok/s (estimated). The best value is the NVIDIA GeForce RTX 3080 10GB (about 73 tok/s for 500 €). The fastest we price is the NVIDIA GeForce RTX 5090, at about 108 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 8k context. On the NVIDIA GeForce RTX 5080 it runs at about 58 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 8k context. On the NVIDIA GeForce RTX 3090 Ti it runs at about 61 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.