We publish our own measurements because vendor tables don't tell you what a $0.99/h endpoint actually does at 260K context. All runs: llama.cpp fork, Qwen3.8-27B, single server, no other tenants. Reproduce anything — configs below.
| SKU | Quant | Context | tok/s (decode) | TTFT | $/hr (us) |
|---|---|---|---|---|---|
| 24GB | MXFP4 + Q4_0 KV | 260,000 ×1 | ~15–40 | — | $0.99 |
| 32GB | MXFP4 + Q4_0 KV | 500,000 ×1 · 260,000 ×2 | — | — | $1.49 |
| 48GB | MXFP4 + Q4_0 KV | 1,000,000 ×1 · 500,000 ×2 · 260,000 ×4 | — | — | $1.99 |
| 96GB | MXFP4 + Q4_0 KV | 1,000,000 ×3 · 750,000 ×4 · 500,000 ×6 · 260,000 ×12 | — | — | $3.49 |
Reference points (community, same model): 218 tok/s single-stream (short ctx) · 140–260 tok/s p50, 0.156s TTFT. TODO at launch: fill TTFT column + link to raw benchmark logs.
| Card | Capacity |
|---|---|
| Blackwell 24 GB | 1 user @ 260K |
| Blackwell 32 GB | 1 user @ 500K · or 2 @ 260K |
| Blackwell 48 GB | 1 user @ 1M · or 2 @ 500K · or 4 @ 260K |
| Blackwell 96 GB | 3 @ 1M · 4 @ 750K · 6 @ 500K · 12 @ 260K |
These are the numbers behind the SKU capacity column on the pricing page. Concurrent users = concurrent in-flight generations (max-num-seqs).
| Benchmark | Qwen3.6-27B | Qwen3.8-27B |
|---|---|---|
| Terminal-Bench 2.1 | 63.4 | 73.0 |
| DeepSWE 1.1 | 13.3 | 42.2 |
| OSWorld-Verified | 63.9 | 84.3 |
| SWE-bench Pro | — | 61.7 |
| LiveCodeBench v6 | — | 90.3 |
Artificial Analysis Intelligence Index: 52 (GLM-5.2: 53, Kimi K3: higher but cluster-scale). #9 on Code Arena WebDev — the only small model in the top 10. Scores are Alibaba's; we flag that instead of hiding it.
10 turns/hr × 200K context + 2K output:
| Option | $/hr |
|---|---|
| noTOKEN.cloud 32GB (dedicated) | $1.49 |
| GLM-5.2 ($1.40/$4.40 per M) | $3.02 |
| Kimi K3 ($3/$15 per M) | $6.75 |
And this is a light workload — 10 turns an hour. At 100 turns/hr × 100K context (10M input tokens/hr), GLM-5.2 reads $14.88/hr and Kimi K3 reads $33/hr, while the dedicated endpoint stays at $1.49. Per-token pricing bills every context re-read; dedicated pricing doesn't care how hard your agent works.