XHToken · Released Oct 19, 2026 · observed 26 Oct 2026
Public-source support evidence
We ran the Q4_K_M GGUF on one Mac; see Hardware notes below. Community MLX weights are available; the architecture is listed in llama.cpp.
XHToken/Spark-X2.6-4B
Spark-X2.6-4B is a text generation model published by XHToken on Hugging Face. We have not written a summary yet; see the model card ↗.
View source model ↗SUPPORT EVIDENCE
The model config architecture is listed in this runtime registry. This is family/architecture evidence only; exact checkpoint loading, model-specific configuration, hardware, and generation were not tested.
Checked 2026-10-27 00:09 UTC
Evidence source ↗The exact model and runtime-specific sources were checked; no positive model-level evidence was established.
Checked 2026-10-26 23:48 UTC
Version v0.40.11
Checked source ↗The exact model and runtime-specific sources were checked; no positive model-level evidence was established.
Checked 2026-10-27 00:28 UTC
Checked source ↗A current public MLX upload with an exact base_model match was observed. Upload availability only; this model was not loaded or hardware-tested.
Checked 2026-10-27 00:09 UTC
Evidence source ↗Checked the exact model config and the runtime architecture registry; no matching declared architecture was found. This is unknown, not evidence of incompatibility.
Checked 2026-10-27 00:09 UTC
Checked source ↗MLX community uploads may target mlx-vlm; an upload observation does not establish mlx-lm compatibility.
MEMORY ESTIMATES
The summary estimate of about 6 GB is the recommended Q4_K_M quant (3.5 GB observed), from file size × 1.2 + 1.5 GB. Each card is the largest observed quant whose estimate fits that capacity.
Which file should I grab?
BF16 · 8.2 GB observed · about 12 GB ↗About 12 GB using file size × 1.2 + 1.5 GB. Fit is an estimate; compatibility, speed, context length and hardware have not been tested.
Which file should I grab?
BF16 · 8.2 GB observed · about 12 GB ↗About 12 GB using file size × 1.2 + 1.5 GB. Fit is an estimate; compatibility, speed, context length and hardware have not been tested.
Which file should I grab?
BF16 · 8.2 GB observed · about 12 GB ↗About 12 GB using file size × 1.2 + 1.5 GB. Fit is an estimate; compatibility, speed, context length and hardware have not been tested.
Which file should I grab?
BF16 · 8.2 GB observed · about 12 GB ↗About 12 GB using file size × 1.2 + 1.5 GB. Fit is an estimate; compatibility, speed, context length and hardware have not been tested.
Which file should I grab?
BF16 · 8.2 GB observed · about 12 GB ↗About 12 GB using file size × 1.2 + 1.5 GB. Fit is an estimate; compatibility, speed, context length and hardware have not been tested.
Which file should I grab?
BF16 · 8.2 GB observed · about 12 GB ↗About 12 GB using file size × 1.2 + 1.5 GB. Fit is an estimate; compatibility, speed, context length and hardware have not been tested.
Which file should I grab?
BF16 · 8.2 GB observed · about 12 GB ↗About 12 GB using file size × 1.2 + 1.5 GB. Fit is an estimate; compatibility, speed, context length and hardware have not been tested.
Which file should I grab?
BF16 · 8.2 GB observed · about 12 GB ↗About 12 GB using file size × 1.2 + 1.5 GB. Fit is an estimate; compatibility, speed, context length and hardware have not been tested.
Memory estimates are the observed file size plus fixed headroom (20% plus 1.5 GB runtime allowance); real needs also depend on context length, KV cache and runtime settings. Fit is an estimate; it does not establish runtime compatibility, speed, context length, or hardware performance. Text-weights-only estimates do not include a projector or total vision memory where unknown.
Terms: a quant is a lower-precision version of the weights; GGUF is a file format used by llama.cpp and compatible apps; MLX targets Apple silicon; vLLM is a model-serving engine for NVIDIA GPUs; the KV cache is stored attention state that grows with context length. Terms explained ↗
OBSERVED FILES
Sizes and file groups come from the listed uploader repositories. A size is marked as an estimated fit only for a complete observed GGUF quant group.
| Uploader | Format & quant | Observed size | Estimated fit | Files |
|---|---|---|---|---|
| XHTokenXHToken/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q4_K_M | 3.5 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file |
| XHTokenXHToken/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q8_0 | 4.4 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file
|
| XHTokenXHToken/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Quant unknown | 8.2 GB | UnknownUnknown: completeness or a complete GGUF quant group was not verified. | 1 file
|
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · IQ2_M | 1.6 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file
|
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · IQ3_M | 2.2 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file
|
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · IQ3_XS | 1.9 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file |
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · IQ3_XXS | 1.8 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file |
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · IQ4_NL | 2.6 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file |
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · IQ4_XS | 2.3 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file |
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q2_K | 1.6 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file
|
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q3_K_L | 2.1 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file |
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q3_K_M | 2.0 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file |
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q3_K_S | 1.9 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file |
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q4_0 | 2.4 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file
|
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q4_1 | 2.6 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file
|
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q4_K_L | 2.8 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file |
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q4_K_M | 2.6 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file |
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q4_K_S | 2.5 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file |
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q5_K_M | 3.2 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file |
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q5_K_S | 3.0 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file |
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q6_K | 3.6 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file
|
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q6_K_L | 3.8 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file |
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q6_K_S | 3.5 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file |
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · Q8_0 | 4.4 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file
|
| bartowskibartowski/Spark-X2.6-4B-GGUF ↗Observed 27 Oct 2026 | GGUF · BF16 | 8.2 GB | 16 GB, 24 GB, 32 GB, 64 GB, 128 GB, 192 GB, 256 GB, 512 GBEstimate only; requires the complete GGUF quant group. | 1 file
|
| mlx-communitymlx-community/Spark-X2.6-4B-OptiQ-4bit ↗Observed 27 Oct 2026 | MLX · Quant unknown | Size unknown | UnknownUnknown: completeness or a complete GGUF quant group was not verified. | 1 file
|
CURATED TRACKING
No curated issues verified for this snapshot. An empty list does not mean there are no bugs.
HARDWARE NOTES
We ran the Q4_K_M GGUF (3.54 GB, XHToken/Spark-X2.6-4B-GGUF @83b47fd) on an Apple M4 Max Mac, 128 GiB unified memory, macOS 27.0.1, Metal with llama.cpp b11912 (upstream) on 26 Oct 2026.
Decode: 107.3 tok/s on a short prompt, 104.1 tok/s on a long prompt (medians of 3 runs). Prefill: 567 / 1,463 tok/s. Time to first token: 49 ms / 1,021 ms.
Peak memory: 4.49 GiB (llama-server footprint). Load time: 13.4 s.
llama-bench: pp512 1,587.8 tok/s, tg128 120.5 tok/s.
Thinking off (enable_thinking=false).
One machine, one run set: temperature 0, 8K context, 1 warm-up plus 3 runs per prompt. Short prompt is 27 tokens; long prompt is 1,488 tokens (each model counts with its own tokenizer). Weights were loaded from an external USB drive with mmap off, so load time is disk-bound. Your speed will differ with hardware, context length and settings.
COMPARE
No comparison page is generated for this model yet. Browse all comparisons →
EMBED
Works in GitHub READMEs and Hugging Face model cards. The badge updates when the site rebuilds.