Ternary Bonsai 2 27B on Dell Precision 7960 Rack (2x RTX PRO 6000, 192 GB)
27.36B on 192 GB at 3,584 GB/s. Hardware details · Model details
Yes. Ternary Bonsai 2 27B fits on Dell Precision 7960 Rack (2x RTX PRO 6000, 192 GB) at the recommended
PTQ1_0 configuration, requiring approximately 7.6 GB at 8K context. Practical context capacity is 256K.CompatibilityComfortable
Calculated fit
Yes
Calculated Uses under 80% of usable memory. Room for a long context and other work.
Recommended quantization
PTQ1_0
Calculated gguf
Memory required
7.6 GB
Calculated of 169.0 GB usable — 5%
Max practical context
256K
Calculated model supports 256K
Memory budget at 8K context
Model weights ⓘ
5.5 GB Measured
KV cache ⓘ
0.5 GB Calculated
Runtime overhead ⓘ
1.6 GB Estimated
Total required
7.6 GB Calculated
Headroom ⓘ
161.4 GB Calculated
Smallest published ternary pack that leaves headroom: uses 5% of usable memory at 8K context.
2 GPUs providing 192 GB aggregate VRAM. Assumes tensor- or layer-parallel sharding; each GPU carries its own context and communication buffers. Interconnect: PCIe 5.0 x16.
Hybrid attention: token-growing KV memory is charged to 16 full-attention blocks. The linear-attention blocks also hold fixed-size state, so the memory estimate is approximate.
Multi-GPU throughput depends heavily on interconnect. Without NVLink or NVSwitch, tensor parallelism over PCIe adds latency that partially offsets the extra bandwidth.
Performance
Estimated performance · recommended PTQ1_0
Decode, prefill and TTFT below are estimates for PTQ1_0. We do not have a comparable PTQ1_0 measurement on this machine.
Estimated decode
—
Estimated PTQ1_0; calculated range
Estimated prefill
—
Estimated PTQ1_0; calculated range
Estimated TTFT at 8K
~0.9–1.9 s
Estimated PTQ1_0; calculated range
Hardware load reference
920 W
Measured machine-level load; not this model run
No throughput figures for this configuration. We do not estimate performance for a model that cannot load.
How the estimate is calculated
- Multi-GPU: 1792 GB/s per card, with each additional card contributing 40% of its bandwidth — 2509 GB/s effective, not the 3584 GB/s aggregate. Cross-GPU collectives use PCIe rather than a dedicated GPU fabric.
- Decode: reading 27.4B active parameters at 1.75 bits/weight takes 3.31 ms at 2509 GB/s x 72% achieved efficiency.
- Per-token overhead of 1.4 ms (kernel launches, attention bookkeeping, sampling) is significant here — this model is not purely bandwidth-bound on this hardware.
- Prefill: 380 TFLOPS (FP16) x 4 for native FP4 tensor cores x 26% assumed model-FLOPs utilisation, divided by 2 x 27.4B parameters per token.
- With few active parameters on fast memory, fixed per-token overhead rather than bandwidth sets the ceiling. Real engines vary widely in how well they hide it.
- Prefill throughput is highly engine-dependent. Flash attention, batch size and quantized KV all move this number substantially, and for sparse mixture-of-experts models it is the least reliable figure we produce.
- This is a calculated estimate, not a measurement. It assumes a single request, a short prompt, no speculative decoding and a warm model already resident in memory.
Estimator version estimator_v1. Stored with every estimated row so old estimates can be regenerated when the model improves.
Submit a benchmarkSubmissions stay pending until reviewed.
This model at other quantizations on this machine
| Quantization | Resident | Disk | Total needed | Utilisation | Fit | Max context |
|---|---|---|---|---|---|---|
PTQ1_0recommended | 5.5 GB | 5.5 GB | 7.6 GB | 5% | Comfortable | 256K |
PQ2_0 | 6.7 GB | 6.7 GB | 8.8 GB | 5% | Comfortable | 256K |
Cost of running Ternary Bonsai 2 27B on this machineUnited States (federal) · C corporation · 8h/day
Monthly economic cost
$467
Calculated after tax
Codex/Claude Code
$100/mo
≈ $100/mo · local is $367 more
Net cash at purchase
$36,663
Calculated VAT not reclaimable
Total over 5 years
$28,021
Calculated after tax, after resale
Cost per USD/1M tokens
—
Calculated
The $100 comparison uses the Codex Pro 5x / Claude Max 5x plans. A fixed planning conversion is used for USD. This compares monthly spend only: subscriptions have usage limits, local hardware has different capabilities and constraints, and taxes or regional pricing may change the charged amount. Prices checked 7 September 2026.
Purchase-price input: $36,663 in United States (federal), tax/VAT excluded · estimated · Dell / EU workstation channel (converted catalogue estimate). This is the localized purchase input; the after-tax economic cost is calculated separately below.
Monthly breakdown
| Depreciation 31,163 over 5 years, straight-line to a 5,499 residual | $519.39 |
| Electricity 51.4 kWh/month at 0.140/kWh | $7.19 |
| Cost of capital 4.0%/yr on 21,081 average capital employed | $70.27 |
| Monthly cost before tax | $596.85 |
| Electricity tax shield Running costs are deductible business expenses | −$1.51 |
| First-year expensing §179 (100.0%) | −$128.32 |
| Monthly economic cost after tax | $467.02 |
Three different numbers, deliberately
Cash cost
$36,663
Money that leaves the bank account on day one, net of reclaimable VAT.
Accounting depreciation
$519.39/month
$31,163 written down over 5 years to a $5,499 residual.
After-tax economic cost
$467.02/month
Depreciation plus running costs plus cost of capital, less the tax those deductions save. This is the figure to compare between machines.
Assumptions and sources (verified 2026-09-07)
VAT rate
0% Official spec
VAT recoverable
0% Official spec
Federal C-corporation estimate at the flat 21% rate. Pass-through entities should use the sole-proprietor estimate as a rougher proxy.
Effective deduction rate
21.00% Calculated
Headline marginal rate 21.00%.
Depreciation
5 years, straight-line Assumption
Residual value
$5,499 (15%) Assumption
Two GPU generations later, the card is worth a fraction of its list price.
Electricity
$0.140/kWh Assumption
Average power draw
292 W Calculated
Load 920 W for 20% of powered hours, idle 135 W for the rest — a machine that is on is not generating tokens the whole time.
Investment allowances
§179 100.0% Official spec
Worth $7,699 in total — first-year expensing that replaces later tax depreciation.
Cost of capital
$70.27/month Assumption
- VAT rate: No US federal VAT · verified 2026-09-07
- Marginal tax rate: IRS Publication 542 — Corporations · verified 2026-09-07
- VAT recoverable fraction: site assumption · verified 2026-09-07
- Useful life: IRS Publication 946 — How To Depreciate Property · verified 2026-09-07
- Electricity price: Site assumption · verified 2026-09-07
Federal planning estimate only, not tax advice. State and local income tax, sales/use tax and incentives are excluded. It assumes 100% business use, a Section 179 election, enough business income to use it, and that the full annual limit remains available.
Ternary Bonsai 2 27B on other hardware
| Hardware | Decode | Price | Fit |
|---|---|---|---|
| RTX 5090 workstation (1x 32 GB) | 121 t/s | $3,332 * | Comfortable |
| Used RTX 4090 workstation (24 GB) | 91.1 t/s | $2,071 * | Comfortable |
Nearest alternatives to the Dell Precision 7960 Rack (2x RTX PRO 6000, 192 GB)
Ternary Bonsai 2 27B on Lenovo ThinkStation PX (4x RTX PRO 6000, 384 GB)384 GBTernary Bonsai 2 27B on CPU-only workstation (Ryzen 9950X, 192 GB DDR5)192 GBTernary Bonsai 2 27B on Mac Studio M2 Ultra 192 GB192 GBTernary Bonsai 2 27B on NVIDIA DGX H200 (8x H200, 1,128 GB)1,128 GBTernary Bonsai 2 27B on Mac Studio M5 Ultra 256 GB256 GB
Compare Dell Precision 7960 Rack (2x RTX PRO 6000, 192 GB) against Lenovo ThinkStation PX (4x RTX PRO 6000, 384 GB) →
Compare Dell Precision 7960 Rack (2x RTX PRO 6000, 192 GB) against Lenovo ThinkStation PX (4x RTX PRO 6000, 384 GB) →