The LPDDR5 memory is listed with a 16GB maximum; no RAM upgrade is assumed.
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 24GB memory and internal storage limit model size; no CUDA support; Amazon main-offer price and stock were not verified in this run.
Listing evidence: 2026-10-03. Apple US launch price announced 22 September 2026: USD 1,699. 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
SparkLLM
Total parameters
4,447,623,680
Exact file size
3,543,441,312 bytes
Quantization / precision
Q4_K_M
Weight repository
XHToken/Spark-X2.6-4B-GGUF
Original model repository
XHToken/Spark-X2.6-4B
Weight revision
83b47fda018fd14f51aa63341f78266f628af5a5
Model revision
66e3ae7bee54e0a523d692cb8ef841f35409807b
Runtime notes
Confirm model architecture and quantization support in your runner.
Recorded release date
2026-10-19
Date evidence
Source repository created 2026-10-19; availability basis, not a proven announcement date. Apache-2.0. Official complete GGUF; llama.cpp b10828 or newer. Source-checkpoint scores are not measured Q4 quality. GGUF metadata reports 4,447,623,680 tensors while source safetensors reports 4,112,079,360 parameters; chart uses the deployed GGUF count. Benchmark table: https://huggingface.co/XHToken/Spark-X2.6-4B/blob/66e3ae7bee54e0a523d692cb8ef841f35409807b/images/all_benchmark.svg
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.
GPQA Diamond
77.1 / 100
Hard science questions. This is a science reasoning test, not an overall intelligence score.
Benchmark efficiency: 21.759 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: Thinking mode high, temperature 1.0, top-p 0.95, top-k -1, from publisher all_benchmark.svg. Harness revision and repeat count are not supplied.
Publisher result; no independent replication or confidence interval supplied. Apache-2.0. Official complete GGUF; llama.cpp b10828 or newer. Source-checkpoint scores are not measured Q4 quality. GGUF metadata reports 4,447,623,680 tensors while source safetensors reports 4,112,079,360 parameters; chart uses the deployed GGUF count. Benchmark table: https://huggingface.co/XHToken/Spark-X2.6-4B/blob/66e3ae7bee54e0a523d692cb8ef841f35409807b/images/all_benchmark.svg Weight size excludes runtime and KV-cache memory; this is not a measured device-fit or speed result.
Following precise instructions. These cards report IFEval without consistently specifying prompt-level versus instruction-level scoring. Treat this view as approximate.
Benchmark efficiency: 26.415 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: Thinking mode high, temperature 1.0, top-p 0.95, top-k -1, from publisher all_benchmark.svg. Harness revision and repeat count are not supplied.
Publisher result; no independent replication or confidence interval supplied. Apache-2.0. Official complete GGUF; llama.cpp b10828 or newer. Source-checkpoint scores are not measured Q4 quality. GGUF metadata reports 4,447,623,680 tensors while source safetensors reports 4,112,079,360 parameters; chart uses the deployed GGUF count. Benchmark table: https://huggingface.co/XHToken/Spark-X2.6-4B/blob/66e3ae7bee54e0a523d692cb8ef841f35409807b/images/all_benchmark.svg Weight size excludes runtime and KV-cache memory; this is not a measured device-fit or speed result.
Competition math from AIME 2026. Published answer accuracy.
Benchmark efficiency: 25.738 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: Thinking mode high, temperature 1.0, top-p 0.95, top-k -1, from publisher all_benchmark.svg. Harness revision and repeat count are not supplied.
Publisher result; no independent replication or confidence interval supplied. Apache-2.0. Official complete GGUF; llama.cpp b10828 or newer. Source-checkpoint scores are not measured Q4 quality. GGUF metadata reports 4,447,623,680 tensors while source safetensors reports 4,112,079,360 parameters; chart uses the deployed GGUF count. Benchmark table: https://huggingface.co/XHToken/Spark-X2.6-4B/blob/66e3ae7bee54e0a523d692cb8ef841f35409807b/images/all_benchmark.svg Weight size excludes runtime and KV-cache memory; this is not a measured device-fit or speed result.
Writing code to solve scientific problems. Published results can depend on the test scaffold.
Benchmark efficiency: 10.385 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: Thinking mode high, temperature 1.0, top-p 0.95, top-k -1, from publisher all_benchmark.svg. Harness revision and repeat count are not supplied.
Publisher result; no independent replication or confidence interval supplied. Apache-2.0. Official complete GGUF; llama.cpp b10828 or newer. Source-checkpoint scores are not measured Q4 quality. GGUF metadata reports 4,447,623,680 tensors while source safetensors reports 4,112,079,360 parameters; chart uses the deployed GGUF count. Benchmark table: https://huggingface.co/XHToken/Spark-X2.6-4B/blob/66e3ae7bee54e0a523d692cb8ef841f35409807b/images/all_benchmark.svg Weight size excludes runtime and KV-cache memory; this is not a measured device-fit or speed result.
Fixing real software issues with tools. Agent setup and external tools affect these scores. File size covers model weights only.
Benchmark efficiency: 17.723 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: Thinking mode high, temperature 1.0, top-p 0.95, top-k -1, from publisher all_benchmark.svg. Harness revision and repeat count are not supplied.
Publisher result; no independent replication or confidence interval supplied. Apache-2.0. Official complete GGUF; llama.cpp b10828 or newer. Source-checkpoint scores are not measured Q4 quality. GGUF metadata reports 4,447,623,680 tensors while source safetensors reports 4,112,079,360 parameters; chart uses the deployed GGUF count. Benchmark table: https://huggingface.co/XHToken/Spark-X2.6-4B/blob/66e3ae7bee54e0a523d692cb8ef841f35409807b/images/all_benchmark.svg 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 3.543 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 3.543 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.