1× Strix Halo
41.3tok/sMixed
1 request, mixed prompt set, with ndt=3 Source
Intelligence40with thinking
- Custom kernel required
- License unclear
Local AI · Recipe · 1× Strix Halo
Qwen3.5-122B-A10B Q4_K_M with llama.cpp on 1× Strix Halo
Qwen3.5-122B-A10B Q4_K_M with llama.cpp on 1× Strix Halo: 28.4 tok/s according to huggingface.co (dataset as of Nov 3, 2026).
by 0xSero
Intelligence (original model) · Artificial Analysisno independent value
Engine
- Engine
- llama.cpp b8746
- Quantization
- GGUF Q4_K_M (4.86 bpw)
- Model family
- Qwen3.5-122B-A10B
- Context
- 262,144
- Parameters
- 99B total / ~10B active (REAP 20 %)
- Creator
- 0xSero
- GitHub stars
- 11
- 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/Qwen3.5-99B-GGUF other
- Base0xSero/Qwen3.5-99B other
- Engine
- llama.cpp b8746
- Context
- 262,144 tokens
Notes
What matters before you rebuild it.
- REAP-pruned
- License unclear
Sources
Related recipes
1× Strix Halo
85.1tok/sPeak
1 request, synthetic prompt Source
Intelligence8with thinkingno thinking 7
1× Strix Halo
70.2tok/sPeak
1 request, synthetic prompt Source
Intelligence18with thinkingno thinking 15
1× Strix Halo
16.3tok/sPeak
1 request, code prompt Source
Intelligence34with thinking
- ≤ 3 bit: quantization may cost quality
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.