whatmodel.sh / Spark-X2.5 1.7B

Spark-X2.5 1.7B

+ contribute

Spark-X2.5 1.7B is an open-weights language model from iFLYTEK (SparkLLM), released August 2026. Its published size is 1.71B parameters and a 1M-token context window. Licence: apache-2.0.

Catalogue identity notes

XHToken/Spark-X2.5-1.7B @14d6e83 (created 2026-08-24, licence apache-2.0). Smaller Spark-X2.5 sibling (Aug 2026). Lab rows from the Spark-X2.5-4B card table (same table prints both sizes).

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 1,707,657,216 parameters.

55.1±1.1#266 of 719 LLMsfrom 17 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of Spark-X2.5 1.7B, out of 828 with a score, then more from iFLYTEK (SparkLLM).

#	model	score	where	RAM	released
318	Qwen2.5 Coder 14B Instruct Alibaba	55±1	local	~10GB	2024-11
319	Qwen3-VL 8B Instruct Alibaba	55±1	api $0.31/M +local	~6.8GB	2025-10
320	Spark-X2.5 1.7B iFLYTEK (SparkLLM)	55±1	local	~2.7GB	2026-08
321	GigaChat 3.5 Ultra Instruct (432B-A28B) Sber	55±1	local	~457GB	2026-07
322	Llama 3.1 405B Instruct Meta	55±1	api $2.40/M +local	~160GB	2024-07
	more from iFLYTEK (SparkLLM)
153	Spark-X2.5 4B iFLYTEK (SparkLLM)	66±1	local	~3.9GB	2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #196 of 300 · 36% of its score · 9 tests

Beats o1 (2024-12-17), o3-mini, DeepSeek R1 (Jan '25) here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Mini, Mellum2 12B-A2.5B Instruct here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
SWE-bench Verified lab	28.3% ✎	▁▁▁▁▁▁▃▄█▆▁▁ beats 16/131	very hard · avg 15%	▇▇▇ 6.7%	sharp · small run
SWE-bench Pro (split unspecified) lab	10.4% ✎	▃·▁▁▁▃▂▃█▇▃▁ beats 8/55	very hard · avg 8.0%	▇▇ 5.7%	sharp · small run
MCP-Atlas (public set) lab	23.4% ✎	▂·▃▂▁·▁▃█▆▆▂ beats 2/37	hard · avg 21%	▇▇ 5.2%	at its level
τ²-bench aggregate lab	65.3% ✎	▁▁▁·▂▂▄▃▃▅█▂ beats 12/37	medium · avg 44%	▇▇ 4.9%	at its level · small run
SWE-bench Multilingual lab	23.3% ✎	▁··▃▃▂▅▇█▃▃▁ beats 1/60	hard · avg 18%	▇▇ 4.6%	at its level
MCPMark lab	2.3% ✎	▃·····█··▃█▃ beats 0/8	very hard · avg 5.4%	▇ 2.9%	too hard for it
BFCL V4 (December 2025 archive) lab	46.9% ✎	▁▁▁▂▇▆▆▆█▂▄▂ beats 65/111	medium · avg 35%	▇ 2.6%	at its level
τ³-bench lab	20.1% ✎	▃·▃·█·▃··▃·▃ beats 6/7	very hard · avg 14%	▇ 2.0%	blunt

1 more test

test	result	vs the others in its run	difficulty	counts	why
BrowseComp lab	29.7% ✎	▅···█·▃···▃▃ beats 6/7	very hard · avg 10%	▇ 1.8%	noisy

coding▁▁▁▃▆██▇▆▄▃▁ #306 of 458 · 20% of its score · 4 tests

Beats Solar Open 100B (102B-A12B), GLM-4.7-Flash, Qwen3 4B Instruct 2507 here, though they rank higher overall. Trails DeepSeek LLM 67B Chat, WizardLM 70B V1.0, Yi 1.5 9B Chat here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
SWE-bench Verified lab	28.3% ✎	▁▁▁▁▁▁▃▄█▆▁▁ beats 16/131	very hard · avg 15%	▇▇▇ 6.7%	sharp · small run
SWE-bench Pro (split unspecified) lab	10.4% ✎	▃·▁▁▁▃▂▃█▇▃▁ beats 8/55	very hard · avg 8.0%	▇▇ 5.7%	sharp · small run
SWE-bench Multilingual lab	23.3% ✎	▁··▃▃▂▅▇█▃▃▁ beats 1/60	hard · avg 18%	▇▇ 4.6%	at its level
SciCode (level unspecified) lab	18.2% ✎	█·····██████ beats 1/6	hard · avg 17%	▇ 2.9%	typical

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #133 of 393 * · 0.4% of its score · 1 test

Beats o3-mini, EXAONE 4.5 33B, INTELLECT-3 here, though they rank higher overall. Trails LFM2.5 8B-A1B, LFM2.5 2.6B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
IFEval (aggregation unspecified) lab	89.5% ✎	▁▁▃▁▂▄▄▆█▃▂▁ beats 110/141	easy · avg 75%	▇ 0.4%	noisy

math▁▂▃▅▆▅▄█▄▁▁▁ #189 of 398 · 40% of its score · 3 tests

Beats MiniMax-M2.1, DeepSeek V3 0324, Qwen3 235B-A22B (Apr 2025, hybrid) here, though they rank higher overall. Trails Phi-4-mini-reasoning 3.8B, DeepSeek R1 Distill Qwen 7B, OpenThinker3 7B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
HMMT February 2026 lab	48.4% ✎	█·▄··▄··▄█·▄ beats 3/7	hard · avg 32%	▇▇▇▇▇▇▇▇ 19%	sharp · at its level
AIME 2026 lab	69.4% ✎	▁▁▁▂▃▂▆█▆▂·▁ beats 9/49	medium · avg 53%	▇▇▇▇ 11%	sharp · at its level
IMO-AnswerBench lab	45.4% ✎	▄▄···▄·▄··█▄ beats 2/6	hard · avg 32%	▇▇▇▇ 10%	at its level

web search█·█▄██·▄▄·▄▄ #2 of 13 * · 1.8% of its score · 1 test

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

test	result	vs the others in its run	difficulty	counts	why
BrowseComp lab	29.7% ✎	▅···█·▃···▃▃ beats 6/7	very hard · avg 10%	▇ 1.8%	noisy

other tests3 not in a task · 20% of its score

test	result	vs the others in its run	difficulty	counts	why
GPQA (subset unspecified) lab	43.8% ✎	█···▃···▅·▃▃ beats 1/7	hard · avg 45%	▇▇▇▇ 9.3%	sharp · at its level
Humanity's Last Exam lab	6.3% ✎	▄▄·▄··▄·▄·▄█ beats 3/7	very hard · avg 3.8%	▇▇▇ 7.9%	too hard for it
IFBench (aggregation unspecified) lab	66.3% ✎	▃▇▂▄▅▅▂▄▄▆█▇ beats 48/80	medium · avg 42%	▇ 2.9%	at its level

$ where to run it

llama.cpp · recommended

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 ↗
Run Spark-X2.5 1.7B · needs ~1.11 GB · from huggingface.co/XHToken
chat in the terminal
llama cli -hf XHToken/Spark-X2.5-1.7B-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf XHToken/Spark-X2.5-1.7B-GGUF:Q4_K_M

LM Studio

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run Spark-X2.5 1.7B · needs ~1.11 GB · from huggingface.co/XHToken
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/XHToken/Spark-X2.5-1.7B-GGUF@Q4_K_M -y
Then run lms ls to see its name, and lms chat followed by that name

Ollama

Install Ollama
download it (macOS / Windows) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run Spark-X2.5 1.7B · needs ~3.4 GB · from ollama.com
chat in the terminal
ollama run SparkLLM/Spark-X2.5-1.7B

Weights and documentation: huggingface.co/XHToken ↗

$ how the score was worked out · XHToken/Spark-X2.5-4B model c… 99%

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

source	results	share of the score	licence
XHToken/Spark-X2.5-4B model card · lab-reported	17	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%	Apache-2.0
prior · pull toward the middle		▇ 1%
weighted average		= 55.1

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit 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 2026-10-11 02:20 UTC · sources and licences · json