Apple · M2 Ultra · 192 GB · Qwen3.8 27B · Q4_K_M at 8K context: ~28 tok/s
Apple Mac Studio M2 Ultra, 192 GB
The most memory Apple sold before the M3 Ultra: 192 GB at 800 GB/s. A 120B model at Q8 or a 235B mixture-of-experts model at Q4 fits. Discontinued, so every listing is used or old stock; the M3 Ultra 256 GB is the current machine a step up.
Lowest price right now
$6,699.99
eBay · free shipping · $34 per GB · observed 2026-11-14 18:37 UTC
Buy the cheapest on eBay, $6,699.99
free shipping · Excellent - Refurbished · itsworthmore 192,084 · 99.6%
Price alert
One email per move, item plus shipping. Clear the price to hear about any drop. Manage alerts.
Price history
Daily low across every tracked vendor, last 4 days.
Where to buy
| Vendor | Price | Condition | Observed | |
|---|---|---|---|---|
| eBay cheapest active listing |
$6,699.99 free shipping |
new and used | 2026-11-14 18:37 UTC | Go to eBay |
On eBay now
4 listings passed our filters at the last check, 7 min ago. We check every 28 minutes. Cheapest delivered first. Seller reputation is feedback count and positive rate.
-
$6,699.99free shipping -
$7,399.99free shipping -
$7,920.30$7,900 + $20.30 shipping -
$8,421.88$8,400 + $21.88 shipping
What it runs
For each model, grouped by vendor with the newest first: the largest quant that fits with 8K of context and the estimated speed for one user, at 8K and at 32K of context. On a card, a model too big for its memory can still run with part of the weights in system RAM; we assume 64 GB, and the speed shown accounts for it. The model you picked on the ladder is highlighted. Estimates from the spec sheet, not measurements: see how we estimate.
| Model | Quant | Needs at 8K | Fit | Max context | Decode at 8K | At 32K | Prefill tok/s |
|---|---|---|---|---|---|---|---|
| DeepSeek | |||||||
| DeepSeek V4.1 Flash 552B-A16B Sep 2026 | IQ2_M | 189 GB | fits | 128K+ | ~67 | ~67 | ~170 |
| DeepSeek V4 Flash 284B-A13B Jul 2026 | Q4_K_M | 175 GB | fits | 128K+ | ~48 | ~43 | ~210 |
| DeepSeek V3.1 671B-A37B Aug 2025 | Q4_K_M | 411 GB | does not fit | ||||
| Gemma | |||||||
| Gemma 4 12B May 2026 | Q8_0 | 14 GB | fits | 128K+ | ~37 | ~36 | ~220 |
| Gemma 4 31B Mar 2026 | Q8_0 | 35 GB | fits | 128K+ | ~14 | ~14 | ~88 |
| Gemma 4 26B-A4B Mar 2026 | Q8_0 | 28 GB | fits | 128K+ | ~82 | ~75 | ~710 |
| Gemma 3 27B Mar 2025 | Q8_0 | 31 GB | fits | 128K+ | ~16 | ~15 | ~98 |
| GLM | |||||||
| GLM-5.3 753B-A40B Aug 2026 | Q4_K_M | 462 GB | does not fit | ||||
| GLM-5.3 Flash 320B-A18B Aug 2026 | Q3_K_M | 159 GB | fits | 128K+ | ~44 | ~40 | ~150 |
| GLM-4.6 355B-A32B Sep 2025 | Q3_K_M | 179 GB | fits | 42K | ~23 | ~16 | ~84 |
| GLM-4.5 Air 106B-A12B Jul 2025 | Q8_0 | 115 GB | fits | 128K+ | ~30 | ~23 | ~220 |
| gpt-oss | |||||||
| gpt-oss-120b Aug 2025 | Q8_0 | 126 GB | fits | 128K+ | ~62 | ~51 | ~530 |
| gpt-oss-20b Aug 2025 | Q8_0 | 24 GB | fits | 128K+ | ~81 | ~68 | ~750 |
| Llama | |||||||
| Llama 4 Scout 109B-A17B Apr 2025 | Q8_0 | 119 GB | fits | 128K+ | ~23 | ~18 | ~160 |
| Llama 3.3 70B Dec 2024 | Q8_0 | 79 GB | fits | 128K+ | ~6.2 | ~5.6 | ~38 |
| Llama 3.1 8B Jul 2024 | Q8_0 | 11 GB | fits | 128K+ | ~50 | ~38 | ~340 |
| MiMo | |||||||
| MiMo V2.6 Pro 1.02T-A42B Sep 2026 | Q4_K_M | 624 GB | does not fit | ||||
| MiMo V2.6 Flash 309B-A15B Sep 2026 | Q4_K_M | 190 GB | fits | 70K | ~43 | ~41 | ~180 |
| Mistral | |||||||
| Mistral Medium 3.5 128B Mar 2026 | Q8_0 | 140 GB | fits | 128K+ | ~3.5 | ~3.3 | ~21 |
| Mistral Small 4 119B-A6.5B Mar 2026 | Q8_0 | 132 GB | fits | 106K | ~36 | ~17 | ~410 |
| Mistral Small 3.2 24B Jun 2025 | Q8_0 | 28 GB | fits | 128K+ | ~18 | ~16 | ~110 |
| Nemotron | |||||||
| Nemotron 3.5 Lightning 30B-A3B Aug 2026 | Q8_0 | 35 GB | fits | 128K+ | ~88 | ~86 | ~770 |
| Qwen | |||||||
| Qwen3.8 Flash-Next 125B-A6B Aug 2026 | Q8_0 | 134 GB | fits | 128K+ | ~58 | ~54 | ~450 |
| Qwen3.8 27B Aug 2026 (your pick) | Q8_0 | 31 GB | fits | 128K+ | ~16 | ~16 | ~100 |
| Qwen3.6 27B Apr 2026 | Q8_0 | 31 GB | fits | 128K+ | ~16 | ~16 | ~100 |
| Qwen3.6 35B-A3B Apr 2026 | Q8_0 | 39 GB | fits | 128K+ | ~95 | ~87 | ~900 |
| Qwen3.5 9B Feb 2026 | Q8_0 | 11 GB | fits | 128K+ | ~49 | ~45 | ~300 |
| Qwen3 Coder 480B-A35B Jul 2025 | IQ2_M | 167 GB | fits | 104K | ~31 | ~22 | ~77 |
| Qwen3 235B-A22B Jul 2025 | Q5_K_M | 170 GB | fits | 119K | ~25 | ~20 | ~120 |
| Qwen3 32B Apr 2025 | Q8_0 | 38 GB | fits | 128K+ | ~13 | ~11 | ~82 |
Specifications
- Memory
- 192 GB LPDDR5 unified
- Memory bandwidth
- 800 GB/s
- Bus width
- 1024-bit
- FP32
- 21.5 TFLOPS
- FP16 (dense)
- 22 TFLOPS
- Form factor
- Desktop box, 197 x 197 x 95 mm
- CPU
- 24-core CPU, 60-core GPU (76-core optional), 32-core Neural Engine
- Architecture
- M2 Ultra
- Launched
- 2023
- MSRP
- $5,599
Source: manufacturer specifications.