buyaigear
Prices checked 8 min ago

Apple · M4 Max · 128 GB · Qwen3.8 27B · Q4_K_M: ~20 tok/s

Apple Mac Studio M4 Max, 128 GB

The same 128 GB as a DGX Spark with twice the bandwidth, in a quiet desktop that is also a Mac. A 70B model at Q4 runs at a usable pace; no CUDA.

Lowest price right now

$4,899

eBay · free shipping · $38 per GB · observed 2026-10-14 22:19 UTC

See it on eBay

Where to buy

VendorPriceConditionObserved
eBay
cheapest active listing		 $4,899
free shipping		 new and used 2026-10-14 22:19 UTC Go to eBay

On eBay now

6 listings passed our filters at the last check. Cheapest delivered first. Seller reputation is feedback count and positive rate.

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. The model you picked on the ladder is highlighted. Estimates from the spec sheet, not measurements: see how we estimate.

ModelQuantNeeds at 8KFitMax contextDecode tok/sPrefill tok/s
DeepSeek
DeepSeek V4.1 Flash 552B-A16B Sep 2026Q4_K_M338 GBdoes not fit
DeepSeek V4 Flash 284B-A13B Jul 2026IQ2_M98 GBfits128K+~74~180
DeepSeek V3.1 671B-A37B Aug 2025Q4_K_M411 GBdoes not fit
Gemma
Gemma 4 12B May 2026Q8_014 GBfits128K+~26~190
Gemma 4 31B Mar 2026Q8_035 GBfits128K+~10~75
Gemma 4 26B-A4B Mar 2026Q8_028 GBfits128K+~81~610
Gemma 3 27B Mar 2025Q8_031 GBfits128K+~11~84
GLM
GLM-5.3 753B-A40B Aug 2026Q4_K_M462 GBdoes not fit
GLM-5.3 Flash 320B-A18B Aug 2026IQ2_M111 GBfits128K+~54~130
GLM-4.6 355B-A32B Sep 2025IQ2_M125 GBfits15K~30~72
GLM-4.5 Air 106B-A12B Jul 2025Q8_0115 GBfits73K~26~190
gpt-oss
gpt-oss-120b Aug 2025Q8_0126 GBfits35K~61~450
gpt-oss-20b Aug 2025Q8_024 GBfits128K+~86~640
Llama
Llama 4 Scout 109B-A17B Apr 2025Q8_0119 GBfits54K~18~140
Llama 3.3 70B Dec 2024Q8_079 GBfits128K+~4.4~33
Llama 3.1 8B Jul 2024Q8_011 GBfits128K+~39~290
MiMo
MiMo V2.6 Pro 1.02T-A42B Sep 2026Q4_K_M624 GBdoes not fit
MiMo V2.6 Flash 309B-A15B Sep 2026IQ2_M107 GBfits128K+~64~150
Mistral
Mistral Medium 3.5 128B Mar 2026Q6_K109 GBfits58K~3.1~18
Mistral Small 4 119B-A6.5B Mar 2026Q6_K104 GBfits47K~61~350
Mistral Small 3.2 24B Jun 2025Q8_028 GBfits128K+~13~96
Qwen
Qwen3.8 Flash-Next 125B-A6B Aug 2026Q6_K104 GBfits128K+~67~380
Qwen3.8 27B Aug 2026 (your pick)Q8_031 GBfits128K+~11~85
Qwen3.6 27B Apr 2026Q8_031 GBfits128K+~11~85
Qwen3.6 35B-A3B Apr 2026Q8_039 GBfits128K+~100~770
Qwen3 Coder 480B-A35B Jul 2025Q4_K_M296 GBdoes not fit
Qwen3 235B-A22B Jul 2025Q3_K_M118 GBfits57K~30~100
Qwen3 32B Apr 2025Q8_038 GBfits128K+~9.4~70

Specifications

Memory
128 GB LPDDR5x unified
Memory bandwidth
546 GB/s
Bus width
512-bit
FP32
18.4 TFLOPS
FP16 (dense)
18 TFLOPS
Form factor
Desktop box, 197 x 197 x 95 mm
CPU
16-core CPU, 40-core GPU, 16-core Neural Engine
Architecture
M4 Max
Launched
2025
MSRP
$3,499

Source: manufacturer specifications.