docs: descriptive model card

README.md

@@ -63,11 +63,13 @@ entrypoint, `prefill`, with a static query width of 64
 | `ctx8192/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64` | 3,989,986,830 | 8192 | main + prefill | same weights, wider manifest |
 | `ctx16384/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64` | 3,989,986,844 | 16384 | main + prefill | same weights, wider manifest |
 | `gpu-pipelined/gemma4_e4b_qat_decode_int4lin` | 3,989,205,604 | 4096 | main | **BLOCKED — see below** |
+| `w4a8/gemma4_e4b_qat_decode_int4lin_a8_tbl_pf64` | 3,990,690,638 | 16384 | main + prefill | **EXPERIMENTAL — see below** |
 
 Each folder holds `<name>.aimodel/` (`main.mlirb` ≈ 3.96 GB, `main.hash`, asset
 `metadata.json`), a bundle-level `metadata.json`, and `tokenizer/` (`tokenizer.json`
 32,169,626 B, `tokenizer_config.json`, `generation_config.json`, `chat_template.jinja`
-18,569 B).
+18,569 B). The `w4a8` folder additionally ships its `calibration_corpus.jsonl`
+(35,045 B).
 
 **The three `_tbl_pf64` folders are the same weights.** `--max-ctx` does not change the
 exported graph — identical function signatures, identical state descriptors, identical
@@ -191,8 +193,23 @@ does not widen the sliding layers' 512-token window.
 | `gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64` (ctx 4096) | **QUALIFIED — measured, viable, not a default.** 10/10 parse, 10/10 enum-clean on the harness above. Slow and memory-bound at the 16 GB tier; it earns a slot only where Gemma's output specifically is wanted. |
 | `ctx8192/…_tbl_pf64` | **QUALIFIED BY EQUIVALENCE, UNMEASURED AT DEPTH** — same weights, same graph, wider manifest integer. No run above 4096 tokens. |
 | `ctx16384/…_tbl_pf64` | **QUALIFIED BY EQUIVALENCE, UNMEASURED AT DEPTH** — as above. |
+| `w4a8/gemma4_e4b_qat_decode_int4lin_a8_tbl_pf64` | **EXPERIMENTAL — built, unmeasured.** Gate: a Mac-side oracle/parity check plus a device benchmark, neither of which has been run. Do not route production traffic to it. |
 | `gpu-pipelined/gemma4_e4b_qat_decode_int4lin` | **BLOCKED — does not load on any current code path.** |
 
+### About the `w4a8` bundle
+
+Same QAT int4 per-block-32 weights and the same graph as
+`gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64`; the difference is an int8
+quantize/dequantize pair on the inputs of every `F.linear`, calibrated on 128 synthetic
+social-media-style samples (the corpus ships in the folder). It was built as a prefill/TTFT
+lever, and its manifest context is 16384.
+
+The caveat is load-bearing and comes from the compression toolchain's own documentation: the
+runtime fast path is `W_INT8 × A_INT8`, and a float weight path executes in floating point
+*regardless* of activation quantization. These weights use int4 scale-multiply dequant, not
+an int8 LUT, so the expected TTFT gain may be **zero or negative**. This bundle exists to be
+measured, not because a win is predicted.
+
 ### Why the non-`tbl` decode bundle is blocked
 
 It declares a **different third input** from the `_tbl` family: