4× RTX PRO 6000
81.7tok/sEveryday
1 request, prose prompt, with MTP Source
Intelligence34with thinkingno thinking 22
- ≤ 3 bit: quantization may cost quality
Local AI · Recipe · 8× RTX PRO 6000
GLM-5.2 744B NVFP4 with vLLM on 8× RTX PRO 6000
Intelligence (original model) · Artificial Analysis34with thinkingno thinking 22
Engine
- Engine
- vLLM fathomless-firmament-v17 (05f50ae)
- Quantization
- NVFP4 (lukealonso/GLM-5.2-NVFP4), A4/A16, optional online MXFP8 dense
- Model family
- GLM-5.2
- Context
- —
- Parameters
- 744B total / 40B active
- Creator
- local-inference-lab
- GitHub stars
- 1,106
- Repo updated
- Jul 15, 2026
Measurements
Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.
No sourced measurements for this recipe.
What you need
- Hardware
- 8 × NVIDIA RTX PRO 6000 Blackwell
- Weights
- Main weightslukealonso/GLM-5.2-NVFP4 MIT
- altlocal-inference-lab/GLM-5.2-NVFP4 MIT
- Basezai-org/GLM-5.2 MIT
- Engine
- vLLM fathomless-firmament-v17 (05f50ae)
Related recipes
4× RTX PRO 6000
70.7tok/sEveryday
1 request, prose prompt, with MTP Source
Intelligence34with thinkingno thinking 22
- ≤ 3 bit: quantization may cost quality
4× RTX PRO 6000
64tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence34with thinkingno thinking 22
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
4× RTX PRO 6000
58.5tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligenceno independent value
- Custom kernel required
4× RTX PRO 6000
104tok/sMixed
1 request, mixed prompt set, with MTP (per recipe) Source
Intelligence34with thinkingno thinking 22
- ≤ 3 bit: quantization may cost quality
4× RTX PRO 6000
92.5tok/sMixed
1 request, mixed prompt set, with MTP Source
Intelligenceno independent value
Local AI in your company?
In a workshop we work out which models and which hardware fit your tasks, and build the first agent on your infrastructure.