diff --git a/docs/gpu-setup-research.md b/docs/gpu-setup-research.md
index 14ce3af..e72d231 100644
--- a/docs/gpu-setup-research.md
+++ b/docs/gpu-setup-research.md
@@ -41,19 +41,20 @@ Best strategy: use local models for routine tasks, save Claude credits for hard
 
 | GPU | Arch | Used Price | TDP | Cooling | Tensor Cores | Mem BW |
 |-----|------|------------|-----|---------|--------------|--------|
-| **Quadro RTX 8000** | Turing (2018) | **$750–1,400** | 260W | Passive variant | Yes (576) | 672 GB/s |
+| **Quadro RTX 8000** | Turing (2018) | **$2,000–2,900** | 260W | Passive variant | Yes (576) | 672 GB/s |
 | **A40** | Ampere (2020) | **~$5,050+** | 300W | Passive | Yes (336 3rd-gen) | 696 GB/s |
 | **RTX A6000** | Ampere (2020) | **~$5,400+** | 300W | Active (blower) | Yes (336 3rd-gen) | 768 GB/s |
 | **L40** | Ada (2022) | **~$6,500+** | 300W | Passive | Yes (568 4th-gen) | 864 GB/s |
 | **RTX 6000 Ada** | Ada (2022) | **~$6,500+** | 300W | Active | Yes (568 4th-gen) | 960 GB/s |
 
 Sources: eBay active/sold listings, GPUPoet price tracking, Pangoly, CamelCamelCamel (all March 2026)
+Note: One outlier RTX 8000 listing at ~$750 exists but is not representative of the market.
 
-### Winner: Quadro RTX 8000 Passive ($750–1,400)
+### Cheapest 48GB Option: Quadro RTX 8000 Passive ($2,000–2,900)
 
-The RTX 8000 is **4–5x cheaper** than every other 48GB option. The passive variant is
-purpose-built for rack servers — no fan, relies on chassis airflow, designed for 24/7 operation
-in 2U/4U systems.
+The RTX 8000 is still the cheapest 48GB card — roughly half the price of an A40 and a
+third of an A6000. The passive variant is purpose-built for rack servers — no fan, relies
+on chassis airflow, designed for 24/7 operation in 2U/4U systems.
 
 Key advantages over the P40:
 - **48GB vs 24GB** — room for models + massive context
@@ -61,6 +62,16 @@ Key advantages over the P40:
 - **NVLink support** — pair two for 96GB combined (100 GB/s bidirectional)
 - 10W idle power draw
 
+### Cost Reality Check
+At $2,000–2,900 the RTX 8000 is a significant investment. The key question: is unified
+48GB VRAM worth 4–6x the cost of dual P40s ($400–500)?
+
+**Yes, if** you need large context windows (32K+) for complex coding — KV cache can't
+be split across two GPUs without NVLink (which P40s don't have).
+
+**No, if** you're mostly doing short-prompt coding tasks and image gen — dual P40s give
+you 48GB total (split) at a fraction of the cost, and each card can handle its own workload.
+
 ## RTX 8000 Performance Benchmarks
 
 ### LLM Inference (Exllama, 5.0 bpw quantization)
@@ -77,6 +88,7 @@ Key advantages over the P40:
 
 | Metric | P40 (24GB) | RTX 8000 (48GB) |
 |--------|-----------|-----------------|
+| **Used price** | **$150–320** | **$2,000–2,900** |
 | 32B model fit | Barely (~2GB free) | Comfortable (~28GB free) |
 | 32B generation speed | ~5-12 t/s (est.) | ~20-34 t/s |
 | Max practical context | ~4K tokens | **32K+ tokens** |
@@ -128,21 +140,22 @@ though still behind Ampere/Ada cards.
 
 ## Recommended Setups
 
-### Best Overall: RTX 8000 Passive ($750–1,400)
+### If budget allows ($2,000–2,900): RTX 8000 Passive
 Single card handles both coding and image gen. 48GB VRAM fits 32B models with massive
-context windows. Passive cooling is rack-native. Tensor cores handle FP16 image gen properly.
-One card, one slot, simple setup.
+context windows (32K+). Passive cooling is rack-native. Tensor cores handle FP16 image gen
+properly. One card, one slot, simple setup. The premium buys you unified VRAM = big context.
 
-### Best Overall + Dedicated Image Gen: RTX 8000 + A2000 ($1,000–1,750)
+### If budget allows + dedicated image gen ($2,300–3,250): RTX 8000 + A2000
 RTX 8000 for coding with full 48GB dedicated to LLM context.
 A2000 for image gen (3x faster than Turing, 70W, bus-powered, blower cooled).
 Best separation of concerns — no model swapping needed.
 
-### Budget Alternative: Dual P40 ($400–500)
+### Best value ($400–500): Dual P40
 Two P40s for 48GB total, but split across cards (can't combine for one model without
-tensor parallelism). One for 32B coding (tight fit), one for image gen (slow, needs --force-fp32).
+NVLink, which P40s lack). One for 32B coding (tight fit, ~4K context), one for image gen
+(slow, needs --force-fp32). **5x cheaper than RTX 8000** but with significant context limitations.
 
-### Cheapest Entry: Single P40 ($200–300)
+### Cheapest entry ($200–300): Single P40
 Run 32B coding model with very limited context (~4K tokens). Swap to image gen when needed.
 Good for testing whether local LLM coding works for your workflow before investing more.