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
InternScience
Total parameters
35,505,251,456
Exact file size
21,713,463,520 bytes
Quantization / precision
Q4_K_M
Weight repository
InternScience/Sage-A1.5-Q4_K_M-GGUF
Original model repository
InternScience/Sage-A1.5
Weight revision
10b179b52f2c841030db327627e707d076b4c8cf
Model revision
0e3205cf441cf01df0c0d238cc4738d0e43b4ca7
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. Official complete Q4_K_M language weights. Source model scores are not measured Q4 quality. Multimodal projector excluded; text comparison only.
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.
SWE-bench Pro · reported
61.2 / 100
Publisher SWE-bench Pro results. Harness, subset and evaluation settings can differ; read each model protocol.
Benchmark efficiency: 2.819 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: mini-SWE-agent, temperature 1.0, top-p 0.95, 200K context with automatic compaction, fully offline. Card does not give repeat count or exact subset/version.
Publisher result; no independent replication or confidence interval supplied. Apache-2.0. Official complete Q4_K_M language weights. Source model scores are not measured Q4 quality. Multimodal projector excluded; text comparison only. 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 21.713 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 21.713 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.