1× DGX Spark
93.1tok/sMixed
1 request, mixed prompt set, with MTP (per recipe) Source
Intelligence18with thinkingno thinking 15
Local AI · Recipe · 1× Strix Halo
Qwen3.6-35B-A3B Q4_K_M with llama.cpp on 1× Strix Halo
Qwen3.6-35B-A3B Q4_K_M with llama.cpp on 1× Strix Halo: 70.2 tok/s according to huggingface.co (dataset as of Nov 3, 2026).
by 0xSero
Intelligence (original model) · Artificial Analysis18with thinkingno thinking 15
Engine
- Engine
- llama.cpp
- Quantization
- GGUF Q4_K_M; Variante DYNAMIC (Mixed per-tensor)
- Model family
- Qwen3.6-35B-A3B
- Context
- —
- Parameters
- 35B total / 3B active
- Creator
- 0xSero
- GitHub stars
- 26
- Repo updated
- May 30, 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
- 1 × AMD Strix Halo
- Weights
- Main weights0xSero/Qwen3.6-35B-GGUF Apache-2.0
- BaseQwen/Qwen3.6-35B-A3B Apache-2.0
- Engine
- llama.cpp
Related recipes
1× DGX Spark
79.7tok/sMixed
1 request, mixed prompt set, with MTP (per recipe) Source
Intelligence18with thinkingno thinking 15
1× DGX Spark
57.5tok/sMixed
1 request, mixed prompt set, with MTP Source
Intelligence18with thinkingno thinking 15
1× DGX Spark
45.4tok/sMixed
1 request, mixed prompt set, no speculative decoding Source
Intelligence18with thinkingno thinking 15
1× Strix Halo
28.4tok/sEveryday
1 request, prose prompt, no speculative decoding Source
Intelligenceno independent value
- License unclear
1× Strix Halo
41.3tok/sMixed
1 request, mixed prompt set, with ndt=3 Source
Intelligence40with thinking
- Custom kernel required
- License unclear
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.