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
KRAFTON
Total parameters
28,783,218,402
Exact file size
19,686,434,304 bytes
Quantization / precision
Q4_K_M
Weight repository
KRAFTON/Raon-1-mini-preview-gguf
Original model repository
KRAFTON/Raon-1-mini-preview
Weight revision
3afcfcdb462ec3995e48099257143c3e352a4471
Model revision
45d2e45c19d8f92b3c0c57b96e975b5fb399bd88
Runtime notes
Confirm model architecture and quantization support in your runner.
Recorded release date
2026-10-21
Date evidence
Source repository created 21 October 2026; repository creation is the availability basis, not an independently confirmed announcement date. Official 30B-A4B preview and complete language GGUF; the separate DFlash draft is excluded.
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.
MMLU-Pro
76.5 / 100
Knowledge and reasoning across many subjects. Published accuracy; different evaluation settings can change the result.
Benchmark efficiency: 3.886 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: KRAFTON source-checkpoint evaluation in thinking mode, temperature 1.0, top-p 0.95, top-k 20; presence penalty 1.5 for knowledge tasks. Repeat count and uncertainty are not stated.
Publisher result, not an independent evaluation. Weight bytes exclude runtime and KV-cache memory. Maximum context does not establish device compatibility. Source evaluation is not a measurement of this Q4_K_M quantization. Apache-2.0; source access requests may be required. Preview specifications can change. Publisher llama.cpp branch is required while upstream support is pending. Source count is 28,783,218,402; GGUF reports 28,783,218,602, a 200-parameter metadata difference. Total stored size, not the 4.3B active count, controls weight memory.
Hard science questions. This is a science reasoning test, not an overall intelligence score.
Benchmark efficiency: 4.282 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: KRAFTON source-checkpoint thinking evaluation, temperature 1.0, top-p 0.95, top-k 20. Repeat count and evaluator revision are not stated.
Publisher result, not an independent evaluation. Weight bytes exclude runtime and KV-cache memory. Maximum context does not establish device compatibility. Source evaluation is not a measurement of this Q4_K_M quantization. Apache-2.0; source access requests may be required. Preview specifications can change. Publisher llama.cpp branch is required while upstream support is pending. Source count is 28,783,218,402; GGUF reports 28,783,218,602, a 200-parameter metadata difference. Total stored size, not the 4.3B active count, controls weight memory.
Solving coding problems. Version 6 only; published pass rates can vary with generation settings.
Benchmark efficiency: 4.145 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: KRAFTON source-checkpoint thinking evaluation, temperature 1.0, top-p 0.95, top-k 20, presence penalty 0 for coding. Repeat count and uncertainty are not stated.
Publisher result, not an independent evaluation. Weight bytes exclude runtime and KV-cache memory. Maximum context does not establish device compatibility. Source evaluation is not a measurement of this Q4_K_M quantization. Apache-2.0; source access requests may be required. Preview specifications can change. Publisher llama.cpp branch is required while upstream support is pending. Source count is 28,783,218,402; GGUF reports 28,783,218,602, a 200-parameter metadata difference. Total stored size, not the 4.3B active count, controls weight memory.
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 19.686 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 19.686 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.