Low-power CPU and shared graphics limit heavy inference.
Listing evidence: 2026-09-25. Amazon.com base price visible in an owner-supplied screenshot reviewed 25 Sep 2026; capture time not supplied. Dated reference, not a live quote. Excludes card signup offers, coupons, tax and shipping.
Fixed 36GB memory and internal storage; no CUDA support; price is a manufacturer reference rather than a verified Amazon offer.
Listing evidence: 2026-10-02. Apple US launch price for the base M5 Max Mac Studio, published 22 September 2026: USD 2,499. Dated manufacturer reference, not an Amazon offer; tax and shipping may differ.
Memory is soldered and shared with the operating system.
Listing evidence: 2026-09-24. GMKtec, EVO-X2 / 64GB / 1TB, recorded 22 Sep 2026; exact ASIN capacity identified 24 Sep. This is a dated reference, not a current Amazon price; tax, shipping and bundle contents may differ.
Weight size is not tested compatibility or speed. Check runtime support and memory for context before buying. Prices are dated references. As an Amazon Associate I earn from qualifying purchases.
How these options are selected
Up to three platforms, with the lowest dated reference price on each. Unknown prices follow known prices. Each memory pool keeps a reserve: 30% (minimum 2 GB) for system or unified memory; 20% (minimum 1 GB) for dedicated VRAM. System RAM is for CPU inference. This check does not establish GPU allocation, software support or context capacity.
Model file and details
Provider
Tencent
Total parameters
30,064,725,888
Exact file size
18,236,702,464 bytes
Quantization / precision
Q4_K_M
Weight repository
tencent/Hy-Memory-30B-A3B-GGUF
Original model repository
tencent/Hy-Memory-30B-A3B
Weight revision
38e10a37701e1caff4a6dc3831448aaf8c2e15d1
Model revision
64a460a94d5498b7316fb02395c72d01c47a7347
Runtime notes
Confirm model architecture and quantization support in your runner.
Recorded release date
2026-10-15
Date evidence
Source repository created 2026-10-15; availability basis, not a proven announcement date. Apache-2.0. 30B-total, about 3B-active memory writer. Official complete standard Q4_K_M, separate from experimental expert quantizations. Source evaluation is not measured Q4 quality.
These scores were compiled from the linked sources. These published scores were not independently tested here. Different prompts, precision, thinking budgets and tools can change results.
Hy-Memory · fixed 20% matrix
55.49 / 100
Equal-weight mean across four memory harnesses, each averaging six metrics on fixed 20% benchmark subsamples. Specialized memory writing, not general intelligence.
Benchmark efficiency: 3.043 published score points per GB of selected weights. This ratio is not an inference-speed measure; check the test settings to see whether the score covers the selected quantization.
Test settings: Table 1 overall macro-average: equal weights across Mem0, Hy-Memory, MemOS and held-out EverMemOS. Each harness averages LoCoMo Judge, LME, PM-v2, Travel SPS, Shopping PS and CMB on fixed 20% subsamples; CMB averages two repository QA evaluations. Not full benchmark scores.
Publisher result; no independent replication or confidence interval supplied. Apache-2.0. 30B-total, about 3B-active memory writer. Official complete standard Q4_K_M, separate from experimental expert quantizations. Source evaluation is not measured Q4 quality. Weight size excludes runtime and KV-cache memory; this is not a measured device-fit or speed result.
Context and version evidence: The repository and file name identify the selected model. Revision hashes are shown above when recorded. Tested context length, full hardware configuration and run date are not consistently recorded in this snapshot. Only settings explicitly stated in each benchmark record are known.
The 18.237 GB figure covers model weights in this file. It excludes the context cache, runtime, operating system and any separate multimodal files. It is not a measured RAM requirement or a token-generation speed.
Confirm model architecture and quantization support in your runner. The selected weights use 18.237 GB; this excludes context cache, runtime buffers and other programs.
These are the first listed tiers that pass our reserve policy, not measured minimum requirements. System RAM and VRAM remain separate. Use the memory tool to change the reserve for your context and runner.