289 reports. These are individual setups, not a controlled benchmark. Qwen3.6 speeds by hardware →
AMD Strix Halo 128GB · llama.cpp
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
User reports Qwen3.6 35B A3B prompt processing at 237.9 t/s at depth 0 on Strix Halo 128GB.
NVIDIA RTX 3090 · llama.cpp · 100,000 ctx
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
User reports MTP improves generation speed by 42% but reduces prompt processing by 18%. MTP requires at least 2GB free VRAM. Without MTP the run reaches 1020/42 t/s; with MTP it reaches 830/60 t/s.
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.
User benchmarks Qwen3.6-27B Q4_K_M on an RX 5700 XT 8GB at 2.70 tok/s. The user also tests Qwen3.5, Qwen3.6-35B-A3B and Gemma-4-31b-it. The user ranks Qwen3.6-27B Q4_K_M second overall for the coding task.
AMD Radeon AI PRO R9700 32GB · llama.cpp · 262,144 ctx
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
User reports Qwen3.6-35B-A3B at 84.48 tokens per second generation and 2000.37 tokens per second prompt eval on a Radeon 9700 with 32GB VRAM. Setup is llama.cpp on Vulkan with the UD-Q5_K_M GGUF, -ngl 99, 262144 context, q8_0 KV cache, flash attention on, batch and ubatch size 2048, 8 threads and parallel 1. With MTP, which the user is now testing, generation is around 110 - 130 t/s and prefill drops to 1700 t/s. ROCm gave much faster prefill but slower generation.
2× V100
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
User reports Qwen3.6 27B at around 80t/s generation and 3000 t/s prompt processing for a single user on V100s. Setup is batch 1 with no MTP, on a multi-card V100 setup whose card count the source does not give. At 128 concurrent requests the same setup reaches 1000 tps generation, which the user says is far removed from what they need.
12× NVIDIA V100 32GB · llama.cpp
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.
User reports Qwen3.5-122B-A10B at 50 t/s and Gemma-4-26B-A4B at 113 t/s on a system with 16 GPUs. The system runs multiple models across the 16 GPUs. User notes hallucinations and pipeline issues.
Intel Arc Pro B70 · llama.cpp · 262,000 ctx
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
User reports creating a poker game without issues. User mentions trying Intel's vLLM fork previously.
NVIDIA RTX Pro 4500 Blackwell 32GB · llama.cpp
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
User benchmarks Qwen3.6 27B IQ4_XS on an RTX Pro 4500 Blackwell 32GB with llama.cpp b9007, reaching 2022.54 t/s prompt processing and 45.19 t/s generation. The same card also runs Qwen3.6 35B-A3B MXFP4 at 5507.10 t/s prompt processing and 159.81 t/s generation, along with Gemma4 26B-A4B MXFP4, Ernie 4.5 21B-A3B MXFP4, Nemotron Cascade 2 30B-A3B MXFP4, Tesselate OmniCoder 9B Q8, Qwen3.5 4B Q4_K, Qwen3.5 9B UD Q4_K_XL and GLM 4.7 Flash MXFP4. Compared with an RTX 5090, the 5090 is 60-70% faster at 2-3x power. User is happy with the card for 24/7 use.
2× AMD Radeon AI PRO R9700 32GB · llama.cpp · 131,072 ctx
User reports 40-67 t/s decode on 2x Radeon AI PRO R9700 32GB at 131,072 context. Setup uses an F16 KV cache. Prefill throughput is 410-1500 t/s. MTP draft acceptance ranges from 0.33-0.61.
2× NVIDIA P102-100 · llama.cpp · 32,768 ctx
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
User reports Qwen3.6-35B-A3B at 23.49 tokens per second per user with 3 concurrent users on two NVIDIA P102-100 cards of 10 GB each. Setup is llama.cpp server with the UD-IQ4_XS GGUF, all layers on the two cards, 96K context giving 32K to each user, with prompt processing at 432.28 tokens per second. The user gives the end result as 70tk/s and 1,257 PP across the three users, from $100 worth of cards.
CMP170HX · NInfer · 262,144 ctx
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
User reports a forked Ninfer on a CMP 170HX roughly doubles performance versus llama.cpp on Qwen3.6-35B-A3B. The setup is used for a Home Assistant voice assistant.
NVIDIA RTX 3090 · llama.cpp · 65,536 ctx
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
User reports Qwen3.6-35B-A3B Q6_K on an RTX 3090 in llama.cpp, with prompt processing improving from 564.5 to 1330.0 tok/s (2.36x) while TG stays at about 97.7 t/s. Setup offloads 8 MoE expert layers to CPU with larger batch sizes, at 64K context and a Q8 KV cache, on a Threadripper PRO 3955WX with about 100 GB DDR4. Measurements are two repetitions with about 1.6% drift.
4× NVIDIA RTX 5060 Ti 16GB · 256,000 ctx
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
User reports 608 t/s cold prefill and 52.2 t/s decode on 4x RTX 5060 Ti 16GB at 256K context. Setup is a Vast AI instance with the Q8 quant, an FP16 KV cache, and MTP enabled. User considers this excellent for $2K hardware.
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.
User reports Qwen 3.6 35B at 50 t/s on Strix Halo. Setup is the Q8_XL quant. User emphasizes energy efficiency and versatility of Strix Halo compared to Nvidia cards.
2× NVIDIA RTX 3090 · llama.cpp
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.
User reports reliable code generation and codebase ingestion with multi-token prediction enabled. Setup uses 96 GB of total VRAM.
2× NVIDIA RTX 3090 Ti · llama.cpp · 196,608 ctx
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.
User reports tensor split-mode raising throughput from 70+ t/s to 100+ t/s, with a peak of 130 t/s. Power draw is 750W+.
M2 Max 96GB · llama.cpp
User reports a vision benchmark champion model at 70 s/img on an Apple M2 Max 96GB with llama.cpp b9690. The model gives the best quality and stability with thinking disabled, and completed 90/90 successful runs.
NVIDIA RTX 5060 Ti 16GB · llama.cpp · 131,072 ctx
Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.
User reports 19 t/s peak and 14 t/s during long generation at 65k context with the KV cache offloaded to RAM via -nkvo, which allows the whole model on GPU with an f16 KV cache. Speed remained similar at 128k context with 63 layers on GPU. Quantizing the KV cache to RAM did not improve performance.
NVIDIA RTX 3090 · Ollama · 32,000 ctx
User reports running Qwen3.6-27B as the reasoning layer in a multi-agent orchestrator for 2 weeks, replacing Claude. Plan generation is good, but tool-call reliability is poor with a 12% format error rate, long-context drift appears past ~14k tokens, and cascade-failure handling is weak. The user concludes the model is viable as a reasoning layer but not as an execution layer.
User runs Qwen3.6-35B-A3B-4bit on an M3 Max 128GB for production sub-agent delegations. User also mentions GLM-5.1 for orchestration. User is considering building a 5090 rig.