selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

XHToken logo

Spark-X2.6-1.7B

XHToken·Instruct·released 19 Oct 2026

Apache 2.01.7B1M ctx ≈1.9 GB
Your GPU
ollama run hf.co/XHToken/Spark-X2.6-1.7B-GGUF:Q4_K_M
All 6 runners ↓

We introduce Spark-X2.6-1.7B, the second model in the Spark-X2.6 series, following the release of Spark-X2.6-4B. Building on Spark-X2.5-1.7B, this release further advances our compact, general-purpose language models for on-device deployment.

Notify me when

How much VRAM does Spark-X2.6-1.7B need?

At Q4_K_M Spark-X2.6-1.7B needs about 1.9 GB with an 8K context (1.9 GB at Q4, 4.3 GB at full precision). Pick your GPU to see what fits and how fast it runs.

--vram
any
--gpus
--quant

Needs: ≈2.7 GB · Q4_K_M · 8K context — Pick a GPU to check the fit.

Change quant, context or KV cache to compare
Advanced: context 8K · KV cache 16-bit
Context
KV cache

Smallest GPU for each quant and context (KV cache 16-bit)

Quantisation8K16K32K64K128K1M
Q3_K_M
Q4_K_M
Q5_K_M
Q6_K
Q8_0
FP16

≤16 GB card24–32 GB48–96 GBmore

QuantisationQualityWeightsKV cacheTotal
Q2_KHeavy lossSmallest, noticeably worse qualityHeavy loss0.5 GB est.0.4 GB≈1.5 GB
Q3_K_MNoticeable lossSmall, some quality lossNoticeable loss0.8 GB est.0.4 GB≈1.8 GB
Q4_K_MrecommendedSmall lossRecommended default for local useSmall loss1.6 GB file0.4 GB≈2.7 GB
Q5_K_MNear-losslessNear-lossless for most tasksNear-lossless1.1 GB est.0.4 GB≈2.1 GB
Q6_KNear-losslessPractically losslessNear-lossless1.3 GB est.0.4 GB≈2.3 GB
Q8_0LosslessLossless in practice, twice the size of Q4Lossless1.7 GB file0.4 GB≈2.7 GB
FP16 / BF16LosslessFull precision, as releasedLossless3.2 GB est.0.4 GB≈4.3 GB

Estimates for 8K tokens of context: weights + KV cache + runtime overhead. Speed assumes memory-bound decoding at your GPU’s bandwidth. Pick a GPU above and the fit column checks every row against it. Weights marked “file” use the real GGUF download size; “est.” rows are computed from the parameter count.

How to pick a quant

Take the biggest quant that fits with room left for context. Q4_K_M is the usual sweet spot. Below Q4 quality drops fast, above Q6 you mostly pay memory for nothing. Big models (70B+, large MoE) tolerate low quants better than small ones.

  • LosslessF16, Q8_0
  • Near-losslessQ6_K, Q5_K_M
  • Small lossQ5_K_S, Q4_K_M, IQ4_NL, IQ4_XS, Q4_K_S
  • Noticeable lossQ4_0, Q3_K_L, Q3_K_M, IQ3_M
  • Heavy lossIQ3_XXS, Q3_K_S, IQ2_M, Q2_K

Typical quality loss, not measured per model. Tiers come from KL divergence against FP16 on Llama 3 8B: llama.cpp perplexity README: LLaMA 3 8B scoreboard (KLD and ΔPPL vs FP16, Wikitext-2); llama.cpp quantize tool: ΔPPL per quant type @ Llama-3-8B

How much context fits?

Model quant
KV cache

At 8K context, Q4_K_M needs ≈2.7 GB(1.6 GB weights + 0.4 GB KV cache + 0.6 GB overhead). Pick a GPU above to see how much context fits.

0204060801K2K4K8K16K32K64K128K256K512K1MGB

Weights + overheadKV cache

Can the RTX 4060 run Spark-X2.6-1.7B? →

Speed vs quality per quant

Smaller quants run faster and fit in less memory, but lose quality.

Q2_KQ3_K_MQ4_K_MQ5_K_MQ6_KQ8_0F16

Fits in VRAMTight fitCPU offload✕ won't runQuality is typical KL divergence vs FP16, not measured for this model.

Real-world speed of Spark-X2.6-1.7B

Tokens per second measured by people running it at home. A GPU shows a median once 3 reports agree on the same setup. Reports far from our estimate wait for a review. Measure yours with llama-bench →

No medians yet. Be one of the first 3 to report a setup.

All reports

Run Spark-X2.6-1.7B locally

--quantQ4_K_Mdefault; pick your GPU to tailor itXHToken/Spark-X2.6-1.7B-GGUF

Q4_K_M straight from Hugging Facedocs
ollama run hf.co/XHToken/Spark-X2.6-1.7B-GGUF:Q4_K_M

Install Ollama

OpenAI-compatible server with a web UIdocs
llama-server -hf XHToken/Spark-X2.6-1.7B-GGUF:Q4_K_M

Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.

Install llama.cpp

Download with the lms CLIdocs
lms get XHToken/Spark-X2.6-1.7B-GGUF@Q4_K_M

Then load it from the LM Studio app or with `lms load`.

Install LM Studio

Apple Silicon with mlx-lmdocs
bash
pip install mlx-lm
mlx_lm.generate --model hermitdave/Spark-X2.6-1.7B-MLX-slq-4.5bpw --prompt "Hello"

Use `mlx_lm.chat` with the same --model for an interactive chat.

OpenAI-compatible serverdocs
mlx_lm.server --model hermitdave/Spark-X2.6-1.7B-MLX-slq-4.5bpw --port 8080

API on http://localhost:8080/v1.

Install MLX

Serve an OpenAI-compatible APIdocs
sglang serve XHToken/Spark-X2.6-1.7B --host 0.0.0.0 --port 30000
Docker Compose (NVIDIA)docs
yaml
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve XHToken/Spark-X2.6-1.7B --host 0.0.0.0 --port 30000
    ports:
      - "30000:30000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

API on port 30000.

Install SGLang

Chat with the pipeline APIdocs
python
from transformers import pipeline

pipe = pipeline("text-generation", model="XHToken/Spark-X2.6-1.7B", dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Explain self-hosting in one paragraph."}]
out = pipe(messages, max_new_tokens=512)
print(out[0]["generated_text"][-1]["content"])

Install Transformers

  • Jancommunity · desktop app
  • KoboldCpp logoKoboldCppcommunity · desktop app
  • LocalAI logoLocalAIcommunity · inference server

Quantised versions and downloads

About Spark-X2.6-1.7B

We introduce Spark-X2.6-1.7B, the second model in the Spark-X2.6 series, following the release of Spark-X2.6-4B. Building on Spark-X2.5-1.7B, this release further advances our compact, general-purpose language models for on-device deployment. Spark-X2.6-1.7B retains exactly the same architecture as Spark-X2.5-1.7B, achieving its capability gains through improved post-training. It delivers substantial improvements in coding, agent, long-context, multilingual, reasoning, etc. These capability gains, combined with strong inference efficiency among models of comparable size, enable more capable and practical on-device AI for developers and users tackling real-world tasks. Technical Highlights: - Stronger Coding, Agentic, and Long-Context Capabilities: The model delivers substantial improvements in complex tool use, multi-step planning, software engineering, and reasoning over extended contexts, achieving state-of-the-art performance among open-source models of comparable size. - Efficient On-Device Inference: The model delivers strong on-device inference efficiency, achieving leading decoding throughput among similarly sized open-source models in our evaluations and enabling more responsive AI experiences on local hardware. - Controllable Thinking Budget: The model provides three configurable thinking levels—none, low, high—allowing applications to balance reasoning quality, latency, and inference cost dynamically.

Full model card on Hugging Face →

Alternatives to Spark-X2.6-1.7B

All alternatives →
LiquidAI logo

LFM3-1.7B

LiquidAI·Chat

≈1.9 GB

LFM3-1.7B is a text model for local agents and specialized applications, based on our new tri-hybrid architecture.

1.7B256K ctx lfm1.0
103.7KOct 2026ollama
openbmb logo

MiniCPM5-2B

openbmb·Chat

≈2.3 GB

We are releasing MiniCPM5-2B, the second model in the MiniCPM5 series, following MiniCPM5-1B. It is a dense 2B Transformer that scales up the same training recipe, built for on-device, local deployment, and resource-constrained scenarios, reaching 2B-class open-source SOTA.

2.5B128K ctx Apache 2.0
1MSept 2026gguf
LiquidAI logo

LFM3-1.7B-Base

LiquidAI·Chat

≈1.9 GB

LFM3-1.7B-Base is the pre-trained checkpoint behind LFM3-1.7B, a text model for local agents and specialized applications based on our new tri-hybrid architecture.

1.7B256K ctx lfm1.0
12KOct 2026ollama
Qwen logo

Qwen3-1.7B

Qwen·Chat

≈2.6 GB

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

2B40K ctx Apache 2.0
3MApr 2025ollama
Qwen logo

Qwen3-1.7B-Base

Qwen·Chat

≈2.4 GB

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

1.7B32K ctx Apache 2.0
618.8KApr 2025gguf
Qwen logo≈1.6 GB

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:

1.5B32K ctx Apache 2.0
5.1MSept 2024ollama

Spark-X2.6-1.7B FAQ

How much VRAM does Spark-X2.6-1.7B need?
About 1.9 GB at Q4_K_M with an 8K context. Q8_0 needs about 2.7 GB and full precision about 4.3 GB. Longer contexts need more memory for the KV cache.
Can Spark-X2.6-1.7B run on the RTX 4060?
Yes. It fits at FP16 / BF16 (about 4.3 GB), at an estimated 44 tokens/s. It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.
Can I use Spark-X2.6-1.7B commercially?
Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.
What is the context length of Spark-X2.6-1.7B?
1,048,576 tokens (1M). The full window needs far more memory than an 8K context.
How do I run Spark-X2.6-1.7B with Ollama or llama.cpp?
With Ollama: ollama run hf.co/XHToken/Spark-X2.6-1.7B-GGUF:Q4_K_M. With llama.cpp: llama-server -hf XHToken/Spark-X2.6-1.7B-GGUF:Q4_K_M, which starts an OpenAI-compatible server.

Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.