Pinned Tweet
Rent RTX PRO 6000 GPUs for $1.89/GPU-hour.
Sign up and get $1 in free credit.
96GB VRAM per GPU for open-model inference and LoRA fine-tuning. Billed per second.
Sign up and get $1 in free credit.
96GB VRAM per GPU for open-model inference and LoRA fine-tuning. Billed per second.
7
1
27
3,299
RTX PRO 6000 GPU rental. 96GB VRAM, from $1.89/GPU-hour, per-second billing. $1 free credit.
ecohash.com/gpu/rtx-pro-60…
ecohash.com/gpu/rtx-pro-60…
13
2
16
1,314
Rent an RTX PRO 6000. 96GB VRAM, from $1.89/GPU-hour. $1 free credit.
ecohash.com/gpu/rtx-pro-60…
ecohash.com/gpu/rtx-pro-60…
5
1
6
1,171
Qwen3.8-27B on one RTX PRO 6000:
1 request: 26.1 output tok/s; 162 ms to first token.
8 concurrent: 179.2 aggregate tok/s; 1.24 s to first token.
Both latencies are P50. Higher throughput comes with a longer wait.
Test conditions + results below.
1 request: 26.1 output tok/s; 162 ms to first token.
8 concurrent: 179.2 aggregate tok/s; 1.24 s to first token.
Both latencies are P50. Higher throughput comes with a longer wait.
Test conditions + results below.
3
1
6
802
BF16, vLLM 0.29.0. 1,024 input / 256 output tokens; ~10-minute runs.
Local synthetic tests; internet/gateway latency excluded. Concurrency 8 is a tested load, not a capacity limit.
ecohash.com/models/qwen3.8…
Local synthetic tests; internet/gateway latency excluded. Concurrency 8 is a tested load, not a capacity limit.
ecohash.com/models/qwen3.8…
0
0
1
622
Launch an 8-GPU RTX PRO 6000 instance on EcoHash.
8 x 96 GB VRAM and a whole node for your workload. Watch the console walkthrough with narration: containers, SSH, HTTP access, and persistent storage.
Full guide: ecohash.com/blog/launch-ei…
8 x 96 GB VRAM and a whole node for your workload. Watch the console walkthrough with narration: containers, SSH, HTTP access, and persistent storage.
Full guide: ecohash.com/blog/launch-ei…
0
0
2
514
1.7B parameters. 3.28% WER. 360x real-time.
Qwen3-ASR-1.7B is the smallest of the three speech-to-text models we serve, and it beats the other two on both accuracy and throughput. Measured end-to-end on EcoHash (RTX Pro 6000).
Same endpoint, $0.05 per 1M input tokens.
Qwen3-ASR-1.7B is the smallest of the three speech-to-text models we serve, and it beats the other two on both accuracy and throughput. Measured end-to-end on EcoHash (RTX Pro 6000).
Same endpoint, $0.05 per 1M input tokens.
0
0
0
384
We ran Qwen-Image-2.1 on a single RTX PRO 6000: 15 fixed-seed prompts, no reruns.
~1 MP: 9.4 s/image, 36.8 GiB peak VRAM
Native 2048²: 52 s, 56.5 GiB
BF16, no quantization or offload
Independent, non-commercial technical evaluation. Method + data:
ecohash.com/blog/qwen-imag…
~1 MP: 9.4 s/image, 36.8 GiB peak VRAM
Native 2048²: 52 s, 56.5 GiB
BF16, no quantization or offload
Independent, non-commercial technical evaluation. Method + data:
ecohash.com/blog/qwen-imag…
0
0
0
320
we just published Qwen-Image-2.1 on RTX PRO 6000: 15-Image Quality and Performance Test medium.com/@ecohash/qwen-…
0
1
1
252
Generated 15 images with Qwen-Image-2.1 on a single NVIDIA RTX PRO 6000.
14 ~1 MP images: 9.378s avg, 36.801 GiB peak.
Native 2048×2048: 52.021s, 56.516 GiB peak.
Prompts + outputs in the replies ↓
ecohash.com/blog/qwen-imag…
14 ~1 MP images: 9.378s avg, 36.801 GiB peak.
Native 2048×2048: 52.021s, 56.516 GiB peak.
Prompts + outputs in the replies ↓
ecohash.com/blog/qwen-imag…
1
0
0
220
14/15 — Prompt
Realistic street-level photo of a minimalist bookstore at blue hour. The illuminated sign reads exactly “微光书店” and “GLOW BOOKS.” Crisp bilingual text, warm shelves visible through glass, softly blurred pedestrians, no other text or logos.
Realistic street-level photo of a minimalist bookstore at blue hour. The illuminated sign reads exactly “微光书店” and “GLOW BOOKS.” Crisp bilingual text, warm shelves visible through glass, softly blurred pedestrians, no other text or logos.
1
0
0
8
