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 · 4× RTX PRO 6000
GLM-5.2 504B NVFP4 with vLLM on 4× RTX PRO 6000
GLM-5.2 504B NVFP4 with vLLM on 4× RTX PRO 6000: 92.5 tok/s according to github.com (dataset as of Nov 3, 2026).
by jcartu
Intelligence (original model) · Artificial Analysisno independent value
Engine
- Engine
- vLLM
- Quantization
- NVFP4 (modelopt) Experten, BF16 Router/Attention, FP8 KV
- Model family
- GLM-5.2
- Context
- 262,144
- Parameters
- 504B
- Creator
- jcartu
- GitHub stars
- 3
- Repo updated
- Jun 21, 2026
Measurements
Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.
Decode · 1 request
Prefill by context
What you need
- Hardware
- 4 × NVIDIA RTX PRO 6000 Blackwell
- Weights
- Main weights0xSero/GLM-5.2-504B MIT
- Engine
- vLLM
- Context
- 262,144 tokens
Notes
What matters before you rebuild it.
- REAP-pruned
Sources
- github.com/jcartu/dsv4-flash-blackwell-inference-study/blob/main/GLM-5.2-504B.md#sustained-decode--aggregate-toks-30-scell
- github.com/jcartu/dsv4-flash-blackwell-inference-study/blob/main/GLM-5.2-504B.md#prefill--toks--ttft
- github.com/jcartu/dsv4-flash-blackwell-inference-study/blob/main/GLM-5.2-504B.md
- github.com/jcartu/dsv4-flash-blackwell-inference-study/blob/main/data/glm52_0xsero_benchmark_results_standard.json
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× DGX Spark
23.7tok/sMixed
1 request, mixed prompt set, with MTP (per recipe) Source
Intelligence34with thinkingno thinking 22
- Experimental
- Custom kernel required
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.