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
Axion1-0
Total parameters
35,107,181,936
Exact file size
21,166,758,336 bytes
Quantization / precision
Q4_K_M
Weight repository
prithivMLmods/Axion-1.0-35B-GGUF
Original model repository
Axion1-0/Axion-1.0-35B
Weight revision
1bbacc9c4f6949b29495e3ef8aec9276c75a0728
Model revision
d4fdb2d6d284ecc24359bfa161a58b835a63c754
Runtime notes
Confirm model architecture and quantization support in your runner.
Recorded release date
2026-11-04
Date evidence
Selected third-party GGUF repository created 4 November 2026; source repository created 16 October. Creation date is not an independently verified public launch date. Reproduction-checkpoint identity reviewed 6 November 2026.
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.
HLE full · Axion reproduction tools
52.8 / 100
Full Humanity's Last Exam in the Axion reproduction tool-using harness. Not comparable to no-tool HLE; detailed sampling and run aggregation are undisclosed.
Benchmark efficiency: 2.494 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: Source card reproduction-checkpoint row, full Humanity's Last Exam with tool-using agent execution. Reference vLLM BF16 serving uses 131,072-token model length, qwen3 reasoning and qwen3_coder tool parser; an external harness executes tools. Exact run count and sampling configuration are not disclosed.
Publisher-reported source-checkpoint result; not an independent test or a score measured on this Q4_K_M file. No confidence interval is supplied. Download bytes cover language weights, not total runtime memory. Apache-2.0. This is a reproduction checkpoint; paper-row results are not transferred. MoE with about 3B active parameters. Source total includes additional weights absent from the text GGUF; selected language-file size excludes the optional 902,822,368-byte vision projector. Tool-augmented HLE is kept separate from closed-book/no-tool HLE. Quantized benchmark quality has not been established.
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 21.167 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.
RAM and VRAM planning for Axion 1.0-35B Reproduction
Confirm model architecture and quantization support in your runner. The selected weights use 21.167 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.