Apple · M3 Ultra · 96 GB · Qwen3.8 27B · Q4_K_M at 8K context: ~29 tok/s
Apple Mac Studio M3 Ultra, 96 GB
The base M3 Ultra: 96 GB at 819 GB/s for the price of one big GPU. A 70B model at Q6 fits with room for context; the 256 GB machine costs $1,500 more and the 512 GB one much more.
Lowest price right now
$4,299
eBay · free shipping · $44 per GB · observed 2026-11-14 18:37 UTC
Buy the cheapest on eBay, $4,299
free shipping · Used · dolphins5464 1,703 · 100.0%
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 6 days.
Where to buy
| Vendor | Price | Condition | Observed | |
|---|---|---|---|---|
| eBay cheapest active listing |
$4,299 free shipping |
new and used | 2026-11-14 18:37 UTC | Go to eBay |
On eBay now
21 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.
-
$4,299free shipping -
$4,341.94$4,250 + $91.94 shipping -
$4,399.95free shipping -
$4,469.99free shipping -
$4,523.83$4,499 + $24.83 shipping -
$4,535.53$4,500 + $35.53 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 | Q4_K_M | 338 GB | does not fit | ||||
| DeepSeek V4 Flash 284B-A13B Jul 2026 | Q4_K_M | 175 GB | does not fit | ||||
| 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+ | ~38 | ~37 | ~220 |
| Gemma 4 31B Mar 2026 | Q8_0 | 35 GB | fits | 128K+ | ~15 | ~14 | ~87 |
| Gemma 4 26B-A4B Mar 2026 | Q8_0 | 28 GB | fits | 128K+ | ~83 | ~77 | ~700 |
| Gemma 3 27B Mar 2025 | Q8_0 | 31 GB | fits | 128K+ | ~17 | ~15 | ~97 |
| GLM | |||||||
| GLM-5.3 753B-A40B Aug 2026 | Q4_K_M | 462 GB | does not fit | ||||
| GLM-5.3 Flash 320B-A18B Aug 2026 | Q4_K_M | 197 GB | does not fit | ||||
| GLM-4.6 355B-A32B Sep 2025 | Q4_K_M | 221 GB | does not fit | ||||
| GLM-4.5 Air 106B-A12B Jul 2025 | Q6_K | 90 GB | fits | 39K | ~38 | ~28 | ~220 |
| gpt-oss | |||||||
| gpt-oss-120b Aug 2025 | Q5_K_M | 85 GB | fits | 128K+ | ~83 | ~63 | ~520 |
| gpt-oss-20b Aug 2025 | Q8_0 | 24 GB | fits | 128K+ | ~83 | ~69 | ~740 |
| Llama | |||||||
| Llama 4 Scout 109B-A17B Apr 2025 | Q6_K | 92 GB | fits | 25K | ~28 | ~160 | |
| Llama 3.3 70B Dec 2024 | Q8_0 | 79 GB | fits | 58K | ~6.3 | ~5.7 | ~38 |
| Llama 3.1 8B Jul 2024 | Q8_0 | 11 GB | fits | 128K+ | ~51 | ~38 | ~330 |
| 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 | does not fit | ||||
| Mistral | |||||||
| Mistral Medium 3.5 128B Mar 2026 | Q5_K_M | 95 GB | fits | 9K | ~5.2 | ~21 | |
| Mistral Small 4 119B-A6.5B Mar 2026 | Q5_K_M | 91 GB | fits | 16K | ~44 | ~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+ | ~90 | ~87 | ~760 |
| Qwen | |||||||
| Qwen3.8 Flash-Next 125B-A6B Aug 2026 | Q5_K_M | 90 GB | fits | 128K+ | ~79 | ~72 | ~440 |
| Qwen3.8 27B Aug 2026 (your pick) | Q8_0 | 31 GB | fits | 128K+ | ~17 | ~16 | ~99 |
| Qwen3.6 27B Apr 2026 | Q8_0 | 31 GB | fits | 128K+ | ~17 | ~16 | ~99 |
| Qwen3.6 35B-A3B Apr 2026 | Q8_0 | 39 GB | fits | 128K+ | ~97 | ~88 | ~890 |
| Qwen3.5 9B Feb 2026 | Q8_0 | 11 GB | fits | 128K+ | ~50 | ~46 | ~300 |
| Qwen3 Coder 480B-A35B Jul 2025 | Q4_K_M | 296 GB | does not fit | ||||
| Qwen3 235B-A22B Jul 2025 | IQ2_M | 83 GB | fits | 74K | ~46 | ~32 | ~120 |
| Qwen3 32B Apr 2025 | Q8_0 | 38 GB | fits | 128K+ | ~13 | ~11 | ~81 |
Specifications
- Memory
- 96 GB LPDDR5 unified
- Memory bandwidth
- 819 GB/s
- Bus width
- 1024-bit
- FP32
- 21.3 TFLOPS
- FP16 (dense)
- 21 TFLOPS
- Form factor
- Desktop box, 197 x 197 x 95 mm
- CPU
- 28-core CPU, 60-core GPU, 32-core Neural Engine
- Architecture
- M3 Ultra
- Launched
- 2025
- MSRP
- $3,999
Source: manufacturer specifications.