readygpu

GLM 4.7 Flash

31.2B total, 5.2B active · 198k context · mit · released 2026-01-19

codingagentic

What to run it on in Germany

Fully in memory at 8k context, priced at retailers today.

Something we price holds it fully in memory, but none reaches 15 tok/s, our bar for recommending it. The table below has the speeds.

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 3090Q5_K_Mfits87 tok/s––
NVIDIA GeForce RTX 5090Q8_0fits117 tok/s––
Mac Studio M4 Max 128GBQ8_0fits37 tok/s––
NVIDIA GeForce RTX 4090Q5_K_Mfits94 tok/s––
Mac mini M4 Pro 64GBQ8_0fits19 tok/s––
AMD Radeon RX 7900 XTXQ5_K_Mfits79 tok/s––
Framework Desktop Ryzen AI Max+ 395 128GBQ8_0fits15 tok/s––
Mac Studio M3 Ultra 512GBQ8_0fits56 tok/s––
NVIDIA DGX Spark 128GBQ8_0fits18 tok/s––
GMKtec EVO-X2 Ryzen AI Max+ 395 128GBQ8_0fits15 tok/s––
Mac Studio M3 Ultra 256GBQ8_0fits56 tok/s––
Mac mini M4 Pro 48GBQ8_0fits19 tok/s––
Mac Studio M4 Max 64GBQ8_0fits37 tok/s––
Mac Studio M3 Ultra 96GBQ8_0fits56 tok/s––
NVIDIA RTX PRO 6000 BlackwellQ8_0fits117 tok/s––
AMD Radeon AI PRO R9700Q8_0fits37 tok/s––
AMD Radeon RX 7900 XTQ4_K_Mfits76 tok/s––
ASUS Ascent GX10 128GBQ8_0fits18 tok/s––
Framework Desktop Ryzen AI Max+ 395 64GBQ8_0fits15 tok/s––
Mac mini M4 32GBQ5_K_Mfits12 tok/s––
NVIDIA GeForce RTX 3090 TiQ5_K_Mfits94 tok/s––
Intel Arc Pro B60Q5_K_Mfits31 tok/s––
NVIDIA Tesla P40Q5_K_Mfits32 tok/s––
NVIDIA GeForce RTX 5070 TiQ4_K_Moffload38 tok/s––
NVIDIA GeForce RTX 5060 Ti 16GBQ4_K_Moffload29 tok/s––
NVIDIA GeForce RTX 3060 12GBQ4_K_Moffload17 tok/s––
AMD Radeon RX 9070 XTQ4_K_Moffload31 tok/s––
NVIDIA GeForce RTX 4060 Ti 16GBQ4_K_Moffload22 tok/s––
NVIDIA GeForce RTX 5080Q4_K_Moffload39 tok/s––
NVIDIA GeForce RTX 4070 Ti SuperQ4_K_Moffload34 tok/s––
NVIDIA GeForce RTX 5070Q4_K_Moffload20 tok/s––
AMD Radeon RX 9060 XT 16GBQ4_K_Moffload22 tok/s––
NVIDIA GeForce RTX 4070 SuperQ4_K_Moffload19 tok/s––
NVIDIA GeForce RTX 4080 SuperQ4_K_Moffload36 tok/s––
AMD Radeon RX 7800 XTQ4_K_Moffload30 tok/s––
Intel Arc B580Q4_K_Moffload16 tok/s––
AMD Radeon RX 7600 XTQ4_K_Moffload20 tok/s––
NVIDIA GeForce RTX 3080 10GBQ4_K_Moffload17 tok/s––
Intel Arc A770 16GBQ4_K_Moffload25 tok/s––

1 other card or machine we price cannot hold it at this context.

Memory needed

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

QuantFile@8k@32k@64k@128k
Q4_K_Mgguf17.1 GB18.2 GB19.6 GB21.4 GB25.1 GB
mlx-4bitmlx15.7 GB16.9 GB18.2 GB20.1 GB23.8 GB
Q5_K_Mgguf19.9 GB21.1 GB22.5 GB24.3 GB28.0 GB
Q6_Kgguf23.0 GB24.2 GB25.5 GB27.4 GB31.1 GB
mlx-8bitmlx29.6 GB30.8 GB32.2 GB34.0 GB37.7 GB
Q8_0gguf29.7 GB30.8 GB32.2 GB34.0 GB37.7 GB

Run it

Copy a command for the runtime you use.

  • Q4_K_M
    • Ollamaollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q4_K_M
    • LM Studiolms get unsloth/GLM-4.7-Flash-GGUF@q4_k_m
    • llama.cppllama-server -hf unsloth/GLM-4.7-Flash-GGUF:Q4_K_M
  • mlx-4bit
    • LM Studiolms get mlx-community/GLM-4.7-Flash-4bit
    • MLXmlx_lm.server --model mlx-community/GLM-4.7-Flash-4bit
  • Q5_K_M
    • Ollamaollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q5_K_M
    • LM Studiolms get unsloth/GLM-4.7-Flash-GGUF@q5_k_m
    • llama.cppllama-server -hf unsloth/GLM-4.7-Flash-GGUF:Q5_K_M
  • Q6_K
    • Ollamaollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q6_K
    • LM Studiolms get unsloth/GLM-4.7-Flash-GGUF@q6_k
    • llama.cppllama-server -hf unsloth/GLM-4.7-Flash-GGUF:Q6_K
  • mlx-8bit
    • LM Studiolms get mlx-community/GLM-4.7-Flash-8bit
    • MLXmlx_lm.server --model mlx-community/GLM-4.7-Flash-8bit
  • Q8_0
    • Ollamaollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q8_0
    • LM Studiolms get unsloth/GLM-4.7-Flash-GGUF@q8_0
    • llama.cppllama-server -hf unsloth/GLM-4.7-Flash-GGUF:Q8_0