whatmodel.sh / Spark-X2.6 1.7B

Spark-X2.6 1.7B

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Spark-X2.6 1.7B is an open-weights language model from iFLYTEK (SparkLLM), released October 2026. Its published size is 1.708B parameters and a 1M-token context window. Licence: apache-2.0.

Catalogue identity notes

Post-trained Spark-X2.6 checkpoint, distinct from X2.5 and Base. Published evaluations use thinking high, temperature 1.0, top_p 0.95, top_k -1. Quantized download quality and speed were not measured in this update.

Model information sources

Release date ↗ · Weights licence ↗ · Parameter count ↗

Hugging Face safetensors metadata: 1,707,657,216 parameters.

58.6±1.0#217 of 732 LLMsfrom 17 benchmark results across 1 source

Score within the LMArena (text) comparison set only.

$ how it compares

The LLMs ranked either side of Spark-X2.6 1.7B, out of 886 with a score, then more from iFLYTEK (SparkLLM).

#modelscorewhereRAMreleased
258Trinity-Large-Preview Arcee AI59±2local~155GB2026-01
259OpenReasoning-Nemotron-32B NVIDIA59±2local~21GB2025-07
260Spark-X2.6 1.7B iFLYTEK (SparkLLM)59±1local~3.4GB2026-10
261EXAONE 4.0 32B LG AI Research59±1local~20GB2025-07
262Phi-4-reasoning-plus 14B Microsoft59±1local~10GB2025-04
more from iFLYTEK (SparkLLM)
126Spark-X2.6 4B iFLYTEK (SparkLLM)67±1local~5.2GB2026-10
169Spark-X2.5 4B iFLYTEK (SparkLLM)65±1local~3.5GB2026-08
347Spark-X2.5 1.7B iFLYTEK (SparkLLM)55±1local~1.9GB2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▄▅▅▄▄▂▁ #140 of 313 · 28% of its score · 7 tests

Beats o3, Gemini 2.5 Pro, Gemini 3.1 Flash-Lite here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Large, GPT-4o (2024-05-13) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
SWE-bench Pro (split unspecified) lab26.7% ✎▂·▁▁▁▁▃▃█▇▂▁ beats 13/58very hard · avg 9.8%▇▇▇ 8.2%sharp
SWE-bench Verified lab59.8% ✎▁▁▁▁▁▁▂▄█▆▁▁ beats 56/138hard · avg 19%▇▇ 3.9%sharp · at its level
BrowseComp lab41.7% ✎▂·▃▁▂▂▆▅█▂▂▄ beats 15/46hard · avg 21%▇ 3.7%at its level
τ²-bench aggregate lab85.3% ✎▁▁▁·▁▁▃▃▃▄█▁ beats 29/39medium · avg 54%▇ 3.7%at its level
SWE-bench Multilingual lab57.3% ✎▁··▁▃▁▅██▂▂▁ beats 19/65hard · avg 25%▇ 3.4%at its level
BFCL V4 (December 2025 archive) lab55.2% ✎▁▁▁▂▆▆▅▆█▂▄▃ beats 85/114medium · avg 40%▇ 3.1%at its level
Humanity's Last Exam with tools lab19.9% ✎▁·▁▂▃▁▄▄▇█▄▅ beats 7/62very hard · avg 11%▇ 2.5%typical
coding▁▁▁▃▅▇█▇▅▄▃▁ #172 of 469 · 19% of its score · 4 tests

Beats Qwen3-Coder-Next (80B-A3B), Gemini 2.5 Pro, Grok 4.1 Fast (Reasoning) here, though they rank higher overall. Trails QwQ-32B-Preview, Ministral 3 8B Reasoning 2512, Phi-4-reasoning 14B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
SWE-bench Pro (split unspecified) lab26.7% ✎▂·▁▁▁▁▃▃█▇▂▁ beats 13/58very hard · avg 9.8%▇▇▇ 8.2%sharp
SWE-bench Verified lab59.8% ✎▁▁▁▁▁▁▂▄█▆▁▁ beats 56/138hard · avg 19%▇▇ 3.9%sharp · at its level
SWE-bench Multilingual lab57.3% ✎▁··▁▃▁▅██▂▂▁ beats 19/65hard · avg 25%▇ 3.4%at its level
SciCode (level unspecified) lab20.1% ✎▁····▃▃▄▅█▆▂ beats 3/40very hard · avg 14%▇ 3.4%typical
chat & writing▁▁▁▃▆▄▆█▆▇▇▃ #149 of 402 * · 2.8% of its score · 1 test

Beats INTELLECT-3, MiniMax-M2, Nemotron 3 Super 120B-A12B here, though they rank higher overall. Trails LFM2.5 1.2B Thinking, LFM2.5 8B-A1B, LFM2.5 2.6B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
IFEval (aggregation unspecified) lab89.4% ✎▁▂▄▂▂▄▆██▅▂▁ beats 110/145easy · avg 83%▇ 2.8%typical
math▁▁▃▅█▆▄█▄▂▁▁ #199 of 431 · 25% of its score · 3 tests

Beats MiniMax-M2.1, DeepSeek V3 (Dec '24), Qwen3 235B-A22B (Apr 2025, hybrid) here, though they rank higher overall. Trails Mixtral 8x7B v0.1 (base), Phi-4-mini-reasoning 3.8B, DeepSeek R1 Distill Qwen 7B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AIME 2026 lab70.1% ✎▁▁▁▂▃▂▆█▆▂·▁ beats 10/52medium · avg 53%▇▇▇▇ 9.1%sharp
HMMT February 2026 lab48.8% ✎▃▃▂▅·████▅▃▅ beats 6/35hard · avg 32%▇▇▇ 8.6%sharp · at its level
IMO-AnswerBench lab47.1% ✎▁▁·▃▁▁▄▆█▄▂▃ beats 4/44hard · avg 32%▇▇▇ 7.4%at its level
web search▅·▅▅█·▃▃▃·▅▃ #3 of 15 * · 6.2% of its score · 2 tests

Beats MiniCPM5 2B, Qwen3.5 9B, Gemma 4 12B here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
BrowseComp lab41.7% ✎▂·▃▁▂▂▆▅█▂▂▄ beats 15/46hard · avg 21%▇ 3.7%at its level
Humanity's Last Exam with tools lab19.9% ✎▁·▁▂▃▁▄▄▇█▄▅ beats 7/62very hard · avg 11%▇ 2.5%typical
other tests5 not in a task · 40% of its score
testresultvs the others in its rundifficultycountswhy
GPQA Diamond lab56.1% ✎▁▁▁▁▂▄▅▅███▄ beats 103/322hard · avg 38%▇▇▇▇▇▇ 15%sharp · at its level
GPQA (subset unspecified) lab51.3% ✎▂▁▂▂▄▃▆▃▅█▃▃ beats 53/106hard · avg 37%▇▇▇▇ 10%sharp · at its level
LongBench v2 lab40.4% ✎▂·▁·▂▃▁▄▄▃█▄ beats 11/33very hard · avg 32%▇▇ 5.8%typical
Humanity's Last Exam lab8.7% ✎▁▁▁▄▆▆▇██▆▁▃ beats 16/111very hard · avg 3.8%▇▇ 5.1%typical
IFBench (aggregation unspecified) lab65.5% ✎▂▆▂▄▄▄▂▄▄▆█▇ beats 48/86medium · avg 49%▇ 3.5%at its level

$ where to run it

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run Spark-X2.6 1.7B · needs ~1.7687 GB · from huggingface.co/XHToken
    chat in the terminal
    llama cli -hf XHToken/Spark-X2.6-1.7B-GGUF
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf XHToken/Spark-X2.6-1.7B-GGUF

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run Spark-X2.6 1.7B · needs ~1.7687 GB · from huggingface.co/XHToken

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/XHToken/Spark-X2.6-1.7B-GGUF -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Spark-X2.6 1.7B · needs ~1.7687 GB · from huggingface.co/XHToken
    chat in the terminal
    ollama run hf.co/XHToken/Spark-X2.6-1.7B-GGUF

Model repository and documentation: huggingface.co/XHToken ↗

$ how the score was worked out · Spark-X2.6 model cards (think… 100%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Spark-X2.6 model cards (thinking high) · maker-reported17Apache-2.0
prior · pull toward the middle
weighted average= 58.6

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json