Pokee-Isaac 28B
enthusiast28B-parameter proprietary non-decoder-only architecture from Pokee AI. The model is pitched as the first real 10M-token context frontier-class agentic model that fits on a single GPU - starting from an RTX 4090 (24GB) for the quantized form.
Vendor-reported highlights. 93.3% RULER at 10M-token context; up to 137K tokens/s prefill on one B200 with a 10M-token context; leads BFCL v4 and tau^3-bench in Pokee’s evaluation; lowest combined attack success rate among evaluated models on the DTAP security red-teaming benchmark.
Deployment and pricing. Closed weights. Hosted API is $0.15/M input, $1/M output. Also deployable in your VPC, on-premises, or on-device with Day-0 support for vLLM and SGLang. Technical docs and API console live at https://console.pokee.ai.
Honest framing. The architecture and most benchmarks are vendor-reported; the 10M context and single-GPU deployment claim are the concrete differentiators to watch as independent evals appear. The 28B size is consistent with the stated RTX 4090 footprint, but treat the throughput and safety numbers as claims until replicated.
- 28.0B
- 10000k
- other
- 🇺🇸 USA
- Aug 2026
What people are building with Pokee-Isaac 28B
Real demos from X
Launch post: 28B, 10M context, single-GPU deployment, $0.15/$1 per 1M tokens View on X →
Scores
Score per dollar
587 pts per $/M input
general_score (88) divided by cheapest input price ($0.15/M). Higher is better value. See live pricing.
Guides covering Pokee-Isaac 28B
Save your hardware and every model page answers the real question: will it run on your machine, and how fast?
Join free - save your rig →Run it locally
Per-quant memory needs and a static "can you run it?" reference - no rig entry required
The reference hardware
22 reference configs, drawn in-house. Scroll for more.
Can you run it? - reference rigs
| Rig | Q4_K_M | Q8_0 | FP16 |
|---|---|---|---|
| NVIDIA Jetson Orin NX 16GB | no -> cloud | no -> cloud | no -> cloud |
| Single GTX 1080 Ti (11GB) | offload | no -> cloud | no -> cloud |
| 4x H100 80GB (320GB) | fast 460.6t/s | fast 263.2t/s | fast 131.6t/s |
| NVIDIA DGX Station 748GB | fast 275.0t/s | fast 157.1t/s | fast 78.6t/s |
| 8x RTX 3090 rack (192GB) | fast 257.4t/s | fast 147.1t/s | fast 73.6t/s |
| 4x RTX 5090 (128GB) | fast 246.4t/s | fast 140.8t/s | fast 70.4t/s |
| AMD Instinct MI300X (192GB) | fast 183.0t/s | fast 104.6t/s | fast 52.3t/s |
| 4x RTX 4090 (96GB) | fast 138.6t/s | fast 79.2t/s | fast 39.6t/s |
| 2x RTX 5090 (64GB) | fast 123.2t/s | fast 70.4t/s | fast 35.2t/s |
| 2x RTX 3090 (48GB) | fast 64.4t/s | fast 36.8t/s | offload |
| Single RTX 5090 (32GB) | fast 61.6t/s | fast 35.2t/s | no -> cloud |
| RTX PRO 6000 Blackwell (96GB) | fast 61.6t/s | fast 35.2t/s | ok 17.6t/s |
| Mac Studio M4 Ultra 192GB | fast 40.9t/s | fast 23.4t/s | ok 11.7t/s |
| Mac Studio M4 Ultra 512GB | fast 40.9t/s | fast 23.4t/s | ok 11.7t/s |
| Single RTX 4090 (24GB) | fast 34.6t/s | offload | no -> cloud |
| MacBook Pro M5 Max 128GB | fast 23.0t/s | ok 13.2t/s | slow 6.6t/s |
| Dual EPYC 9004 + 768GB DDR5-4800 | ok 15.8t/s | ok 9.1t/s | slow 4.5t/s |
| DGX Spark 128GB unified | ok 9.4t/s | slow 5.4t/s | slow 2.7t/s |
| Ryzen AI Max+ 395 128GB | ok 8.8t/s | slow 5.0t/s | slow 2.5t/s |
| Jetson AGX Orin 64GB | slow 7.0t/s | slow 4.0t/s | slow 2.0t/s |
| Epyc + 512GB DDR4-3200 + 2x RTX 3090 | slow 7.0t/s | slow 4.0t/s | slow 2.0t/s |
| Epyc + 512GB DDR4-2400 + 2x RTX 3090 | slow 5.3t/s | slow 3.0t/s | slow 1.5t/s |
Fit tiers use the same will-it-run logic as the rig finder. For comfortable fits, the badge reflects decode speed: fast >=20 t/s, ok 8-20 t/s, slow <8 t/s. t/s is a bandwidth estimate, not a measured benchmark.
Download options
Or run it in the cloud
Live per-provider pricing, throughput and uptime - refreshed about 2 months ago via OpenRouter. Click a column to sort.
some pricing may be stale - last verified 2026-08-05
| Provider | Type | Input $/M | Output $/M | Cache $/M | Tok/s | Latency | Uptime | Value |
|---|---|---|---|---|---|---|---|---|
|
Pokee AI
stale
|
API | 0.15 | 1.00 | - | - | - | - | cheapest |
Default order: throughput among 95%+ uptime providers, then latency; subscriptions last. Sort by any column. Subscription rows show $/mo in the Value column - per-token columns are "-". Affiliate links are marked sponsored / nofollow. Confirm current pricing on the provider's site before committing.
Detailed API pricing page + JSON endpoint →
Inference cost over time
Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.