Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
C++
DeepSeek quality numbers from the final-tip scores (H100, 4,995 positions): 2.00 KL 0.170 ppl +15.5% (code +8.6%, agent +5.3%), 2.25 KL 0.107 ppl +7.3% (code +3.2%, agent +2.2%); README x7, DEEPSEEK41.md, release notes, setup and fit text
Niko12215353097c9093
diff --git a/README.de.md b/README.de.mdindex fd164c25a..e422baeec 100644--- a/README.de.md+++ b/README.de.md@@ -197,8 +197,8 @@ Alle Größen, Downloads und was wo läuft: [docs/MODELS.md](docs/MODELS.md).| Set | Download | Qualität im Vergleich zum Originalmodell | Antwortet mit || --- | ---: | --- | --- || **IQ1_M** (1,75 Bit) | 239 GB | KL 0,217, Perplexität 3,80 (+21 %); Code +8,9 %, Agent-Aufgaben +10,2 %; schwächer bei einfacher englischer Prosa. Laut Modellkarte von ISTA-DASLab behält es 98,7 % des Aufgabendurchschnitts des Basismodells (AIME25, GPQA-Diamond, LiveCodeBench v6). | noch nicht gemessen |-| **IQ2_XXS** (2.00 Bit) | 257 GB | KL 0,169, Perplexität 3,64 (+16 %) | 6 bis 9 Tokens/s auf einer RTX 3060, etwa 5 auf einer RTX 5070 |-| **IQ2_XS** (2.25 Bit) | 274 GB | KL 0,110, Perplexität 3,40 (+8 %); Code +3,5 %, Agent-Aufgaben +2,5 % | etwa 11 Tokens/s auf einer Radeon AI PRO R9700 |+| **IQ2_XXS** (2.00 Bit) | 257 GB | KL 0,170, Perplexität 3,63 (+15,5 %); Code +8,6 %, Agent-Aufgaben +5,3 % | 6 bis 9 Tokens/s auf einer RTX 3060, etwa 5 auf einer RTX 5070 |+| **IQ2_XS** (2.25 Bit) | 274 GB | KL 0,107, Perplexität 3,37 (+7,3 %); Code +3,2 %, Agent-Aufgaben +2,2 % | etwa 11 Tokens/s auf einer Radeon AI PRO R9700 || **IQ4_NL** (Engram-Tabelle, kein drittes Modell) | 111 GB, schon in allen drei Downloads oben enthalten | Die 4-Bit-Engram-Nachschlagetabelle, die das Modell aus RAM oder SSD liest. Alle drei Sets nutzen diese eine Datei (`DeepSeek-V4.1-Flash-Engram-IQ4_NL.gguf`). | n/a |4x Radeon AI PRO R9700: etwa 31 Tokens/s, 55 bis 69 mit DSpark.diff --git a/README.es.md b/README.es.mdindex 2b17edbf7..c90d47fd9 100644--- a/README.es.md+++ b/README.es.md@@ -197,8 +197,8 @@ Todos los tamaños, descargas y lo que cabe en cada equipo: [docs/MODELS.md](doc| Conjunto | Descarga | Calidad frente al modelo original | Responde a || --- | ---: | --- | --- || **IQ1_M** (1,75 bits) | 239 GB | KL 0,217, perplejidad 3,80 (+21 %); código +8,9 %, tareas de agente +10,2 %; más débil con prosa inglesa corriente. Según la ficha del modelo de ISTA-DASLab, conserva el 98,7 % del promedio de tareas del modelo base (AIME25, GPQA-Diamond, LiveCodeBench v6). | aún sin medir |-| **IQ2_XXS** (2.00 bits) | 257 GB | KL 0,169, perplejidad 3,64 (+16 %) | de 6 a 9 tokens/s en una RTX 3060, unos 5 en una RTX 5070 |-| **IQ2_XS** (2.25 bits) | 274 GB | KL 0,110, perplejidad 3,40 (+8 %); código +3,5 %, tareas de agente +2,5 % | unos 11 tokens/s en una Radeon AI PRO R9700 |+| **IQ2_XXS** (2.00 bits) | 257 GB | KL 0,170, perplejidad 3,63 (+15,5 %); código +8,6 %, tareas de agente +5,3 % | de 6 a 9 tokens/s en una RTX 3060, unos 5 en una RTX 5070 |+| **IQ2_XS** (2.25 bits) | 274 GB | KL 0,107, perplejidad 3,37 (+7,3 %); código +3,2 %, tareas de agente +2,2 % | unos 11 tokens/s en una Radeon AI PRO R9700 || **IQ4_NL** (tabla Engram, no es un tercer modelo) | 111 GB, ya incluidos en las tres descargas de arriba | La tabla de consulta Engram de 4 bits que el modelo lee de la RAM o del SSD. Los tres conjuntos usan este único archivo (`DeepSeek-V4.1-Flash-Engram-IQ4_NL.gguf`). | n/a |4x Radeon AI PRO R9700: unos 31 tokens/s, de 55 a 69 con DSpark.diff --git a/README.fr.md b/README.fr.mdindex a5516652d..9661a6bd4 100644--- a/README.fr.md+++ b/README.fr.md@@ -198,8 +198,8 @@ Toutes les tailles, les téléchargements et ce qui tient où : [docs/MODELS.md]| Version | Téléchargement | Qualité par rapport au modèle d’origine | Écrit à || --- | ---: | --- | --- || **IQ1_M** (1,75 bit) | 239 Go | KL 0,217, perplexité 3,80 (+21 %) ; code +8,9 %, tâches d’agent +10,2 % ; plus faible sur la prose anglaise courante. D’après la fiche du modèle d’ISTA-DASLab, elle garde 98,7 % de la moyenne des tâches du modèle de base (AIME25, GPQA-Diamond, LiveCodeBench v6). | pas encore mesurée |-| **IQ2_XXS** (2.00 bits) | 257 GB | KL 0,169, perplexité 3,64 (+16 %) | 6 à 9 tokens/s sur une RTX 3060, environ 5 sur une RTX 5070 |-| **IQ2_XS** (2.25 bits) | 274 GB | KL 0,110, perplexité 3,40 (+8 %) ; code +3,5 %, tâches d’agent +2,5 % | environ 11 tokens/s sur une Radeon AI PRO R9700 |+| **IQ2_XXS** (2.00 bits) | 257 GB | KL 0,170, perplexité 3,63 (+15,5 %) ; code +8,6 %, tâches d’agent +5,3 % | 6 à 9 tokens/s sur une RTX 3060, environ 5 sur une RTX 5070 |+| **IQ2_XS** (2.25 bits) | 274 GB | KL 0,107, perplexité 3,37 (+7,3 %) ; code +3,2 %, tâches d’agent +2,2 % | environ 11 tokens/s sur une Radeon AI PRO R9700 || **IQ4_NL** (table Engram, pas un troisième modèle) | 111 Go, déjà compris dans les trois téléchargements ci-dessus | La table de consultation Engram en 4 bits que le modèle lit dans la RAM ou sur le SSD. Les trois versions utilisent ce seul fichier (`DeepSeek-V4.1-Flash-Engram-IQ4_NL.gguf`). | n/a |4x Radeon AI PRO R9700 : environ 31 tokens/s, 55 à 69 avec DSpark.diff --git a/README.ja.md b/README.ja.mdindex 07a2f41df..b3ba4196c 100644--- a/README.ja.md+++ b/README.ja.md@@ -190,8 +190,8 @@ Gyro は NVIDIA と AMD のカード(AMD は実験的)、および Linux 上| セット | ダウンロード | 元のモデルとの品質差 | 出力速度 || --- | ---: | --- | --- || **IQ1_M**(1.75 ビット) | 239 GB | KL 0.217、パープレキシティ 3.80(+21%)、コード +8.9%、エージェント作業 +10.2%、通常の英語の散文では弱めです。ISTA-DASLab のモデルカードによると、基本モデルのタスク平均の 98.7% を保ちます(AIME25、GPQA-Diamond、LiveCodeBench v6)。 | 未測定 |-| **IQ2_XXS** (2.00 ビット) | 257 GB | KL 0.169、パープレキシティ 3.64(+16%) | RTX 3060 で毎秒 6 から 9 トークン、RTX 5070 で約 5 |-| **IQ2_XS** (2.25 ビット) | 274 GB | KL 0.110、パープレキシティ 3.40(+8%)、コード +3.5%、エージェント作業 +2.5% | Radeon AI PRO R9700 1 枚で毎秒約 11 トークン |+| **IQ2_XXS** (2.00 ビット) | 257 GB | KL 0.170、パープレキシティ 3.63(+15.5%)、コード +8.6%、エージェント作業 +5.3% | RTX 3060 で毎秒 6 から 9 トークン、RTX 5070 で約 5 |+| **IQ2_XS** (2.25 ビット) | 274 GB | KL 0.107、パープレキシティ 3.37(+7.3%)、コード +3.2%、エージェント作業 +2.2% | Radeon AI PRO R9700 1 枚で毎秒約 11 トークン || **IQ4_NL**(Engram テーブル、3 つ目のモデルではありません) | 111 GB、上の 3 つのダウンロードに含まれています | モデルが RAM または SSD から読む 4 ビットの Engram 参照テーブルです。3 つのセットはこの 1 つのファイル(`DeepSeek-V4.1-Flash-Engram-IQ4_NL.gguf`)を共有します。 | 該当なし |Radeon AI PRO R9700 4 枚:毎秒約 31 トークン、DSpark ありで 55 から 69。diff --git a/README.md b/README.mdindex c41f87ae6..06b39950c 100644--- a/README.md+++ b/README.md@@ -195,8 +195,8 @@ Every size, download and what fits where: [docs/MODELS.md](docs/MODELS.md).| Set | Download | Quality against the original model | Writes at || --- | ---: | --- | --- || **IQ1_M** (1.75 bits) | 239 GB | KL 0.217, perplexity 3.80 (+21%); code +8.9%, agent work +10.2%; weaker on plain English prose. ISTA-DASLab's model card: keeps 98.7% of the base model's task average (AIME25, GPQA-Diamond, LiveCodeBench v6). | not measured yet |-| **IQ2_XXS** (2.00 bits) | 257 GB | KL 0.169, perplexity 3.64 (+16%) | 6 to 9 tokens/s on an RTX 3060, about 5 on an RTX 5070 |-| **IQ2_XS** (2.25 bits) | 274 GB | KL 0.110, perplexity 3.40 (+8%); code +3.5%, agent work +2.5% | about 11 tokens/s on one Radeon AI PRO R9700 |+| **IQ2_XXS** (2.00 bits) | 257 GB | KL 0.170, perplexity 3.63 (+15.5%); code +8.6%, agent work +5.3% | 6 to 9 tokens/s on an RTX 3060, about 5 on an RTX 5070 |+| **IQ2_XS** (2.25 bits) | 274 GB | KL 0.107, perplexity 3.37 (+7.3%); code +3.2%, agent work +2.2% | about 11 tokens/s on one Radeon AI PRO R9700 || **IQ4_NL** (Engram table, not a third model) | 111 GB, already in all three downloads above | The 4-bit Engram lookup table the model reads from RAM or SSD. All three sets use this one file (`DeepSeek-V4.1-Flash-Engram-IQ4_NL.gguf`). | n/a |4x Radeon AI PRO R9700: about 31 tokens/s, 55 to 69 with DSpark.diff --git a/README.pt-BR.md b/README.pt-BR.mdindex 4b75f7683..7fe4ac539 100644--- a/README.pt-BR.md+++ b/README.pt-BR.md@@ -190,8 +190,8 @@ Todos os tamanhos, downloads e o que cabe em cada configuração: [docs/MODELS.m| Conjunto | Download | Qualidade em relação ao modelo original | Responde a || --- | ---: | --- | --- || **IQ1_M** (1,75 bits) | 239 GB | KL 0,217, perplexidade 3,80 (+21%); código +8,9%, tarefas de agente +10,2%; mais fraco em prosa comum em inglês. Segundo o cartão do modelo da ISTA-DASLab, mantém 98,7% da média de tarefas do modelo base (AIME25, GPQA-Diamond, LiveCodeBench v6). | ainda não medida |-| **IQ2_XXS** (2.00 bits) | 257 GB | KL 0,169, perplexidade 3,64 (+16%) | 6 a 9 tokens/s em uma RTX 3060, cerca de 5 em uma RTX 5070 |-| **IQ2_XS** (2.25 bits) | 274 GB | KL 0,110, perplexidade 3,40 (+8%); código +3,5%, tarefas de agente +2,5% | cerca de 11 tokens/s em uma Radeon AI PRO R9700 |+| **IQ2_XXS** (2.00 bits) | 257 GB | KL 0,170, perplexidade 3,63 (+15,5%); código +8,6%, tarefas de agente +5,3% | 6 a 9 tokens/s em uma RTX 3060, cerca de 5 em uma RTX 5070 |+| **IQ2_XS** (2.25 bits) | 274 GB | KL 0,107, perplexidade 3,37 (+7,3%); código +3,2%, tarefas de agente +2,2% | cerca de 11 tokens/s em uma Radeon AI PRO R9700 || **IQ4_NL** (tabela Engram, não é um terceiro modelo) | 111 GB, já incluídos nos três downloads acima | A tabela de consulta Engram de 4 bits que o modelo lê da RAM ou do SSD. Os três conjuntos usam este único arquivo (`DeepSeek-V4.1-Flash-Engram-IQ4_NL.gguf`). | n/a |4x Radeon AI PRO R9700: cerca de 31 tokens/s, 55 a 69 com DSpark.diff --git a/README.zh-CN.md b/README.zh-CN.mdindex 98e313c66..cab50bb0b 100644--- a/README.zh-CN.md+++ b/README.zh-CN.md@@ -189,8 +189,8 @@ Gyro 可在 NVIDIA 和 AMD 显卡(AMD 为实验性支持)以及 Linux 上的| 版本 | 下载大小 | 与原模型相比的质量 | 生成速度 || --- | ---: | --- | --- || **IQ1_M**(1.75 位) | 239 GB | KL 0.217,困惑度 3.80(+21%);代码 +8.9%,智能体任务 +10.2%;普通英文散文表现较弱。据 ISTA-DASLab 的模型卡,它保留了基础模型任务平均分的 98.7%(AIME25、GPQA-Diamond、LiveCodeBench v6)。 | 尚未测量 |-| **IQ2_XXS** (2.00 位) | 257 GB | KL 0.169,困惑度 3.64(+16%) | RTX 3060 上每秒 6 到 9 个 token,RTX 5070 上约 5 个 |-| **IQ2_XS** (2.25 位) | 274 GB | KL 0.110,困惑度 3.40(+8%);代码 +3.5%,智能体任务 +2.5% | 一块 Radeon AI PRO R9700 上每秒约 11 个 token |+| **IQ2_XXS** (2.00 位) | 257 GB | KL 0.170,困惑度 3.63(+15.5%);代码 +8.6%,智能体任务 +5.3% | RTX 3060 上每秒 6 到 9 个 token,RTX 5070 上约 5 个 |+| **IQ2_XS** (2.25 位) | 274 GB | KL 0.107,困惑度 3.37(+7.3%);代码 +3.2%,智能体任务 +2.2% | 一块 Radeon AI PRO R9700 上每秒约 11 个 token || **IQ4_NL**(Engram 表,不是第三个模型) | 111 GB,已包含在上面三个下载中 | 模型从内存或固态硬盘读取的 4 位 Engram 查找表。三个版本共用这一个文件(`DeepSeek-V4.1-Flash-Engram-IQ4_NL.gguf`)。 | 不适用 |4 块 Radeon AI PRO R9700:每秒约 31 个 token,使用 DSpark 时为 55 到 69。diff --git a/docs/DEEPSEEK41.md b/docs/DEEPSEEK41.mdindex da2073886..e3ad46cbd 100644--- a/docs/DEEPSEEK41.md+++ b/docs/DEEPSEEK41.md@@ -28,8 +28,8 @@ with an out-of-memory message. Both are said before anything is downloaded.Setup offers three official sets (ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF, pinned): **IQ1_M, 1.75 bpw** (`ist-das-1.75bpw`, 121 GB, slightly lower quality; setup recommends it where 2.00 is tight in memory or disk), **IQ2_XXS, 2.00 bpw** (138 GB) and **IQ2_XS, 2.25 bpw** (155 GB). All use thesame 111 GB n-gram table (downloaded once into `models/deepseek-v4.1-flash-shared`) and the 8 GB DSpark drafter: 257 GB of disk for-2.00, 274 GB for 2.25, 239 GB for 1.75, 533 GB for all three. Quality against the original model: perplexity +16% on 2.00, +8% on 2.25 (code and agent work-about +3.5% / +2.5% on 2.25). IQ1_M: perplexity +21% (KL 0.217, top-1 82.5%); code +8.9%, agent work +10.2%, multilingual +14%, docs +24%, plain English prose +53%, so it is weaker on prose. ISTA-DASLab's model card says it keeps 98.7% of the base model's task average (AIME25, GPQA-Diamond, LiveCodeBench v6).+2.00, 274 GB for 2.25, 239 GB for 1.75, 533 GB for all three. Quality against the original model (4,995 positions, the final files): 2.00 has KL 0.170 and perplexity +15.5% (code +8.6%, agent work +5.3%); 2.25 has KL 0.107 and+perplexity +7.3% (code +3.2%, agent work +2.2%). IQ1_M: perplexity +21% (KL 0.217, top-1 82.5%); code +8.9%, agent work +10.2%, multilingual +14%, docs +24%, plain English prose +53%, so it is weaker on prose. ISTA-DASLab's model card says it keeps 98.7% of the base model's task average (AIME25, GPQA-Diamond, LiveCodeBench v6).| File | Size | What it is || --- | ---: | --- |diff --git a/docs/release-notes-0.2.4.md b/docs/release-notes-0.2.4.mdindex 5c6887811..ca06dd10e 100644--- a/docs/release-notes-0.2.4.md+++ b/docs/release-notes-0.2.4.md@@ -10,9 +10,9 @@ Strata now runs DeepSeek V4.1-Flash on a PC with one 12 GB graphics card and 46| set | download | quality against the original model ||---|---|---|- | IQ1_M (1.75 bits) | 239 GB | perplexity +21%; code and agent text +8.9% and +10.2%; weaker on plain English prose. ISTA-DASLab's model card: keeps 98.7% of the base model's task average (AIME25, GPQA-Diamond, LiveCodeBench v6) |- | IQ2_XXS (2.00 bits) | 257 GB | perplexity +16%; code and agent text +8.5% and +5.9% |- | IQ2_XS (2.25 bits) | 274 GB | perplexity +7.7% to +8.3%; code and agent text +3.5% and +2.5% |+ | IQ1_M (1.75 bits) | 239 GB | perplexity +21% (KL 0.217); code and agent text +8.9% and +10.2%; weaker on plain English prose. ISTA-DASLab's model card: keeps 98.7% of the base model's task average (AIME25, GPQA-Diamond, LiveCodeBench v6) |+ | IQ2_XXS (2.00 bits) | 257 GB | perplexity +15.5% (KL 0.170); code and agent text +8.6% and +5.3% |+ | IQ2_XS (2.25 bits) | 274 GB | perplexity +7.3% (KL 0.107); code and agent text +3.2% and +2.2% || IQ4_NL (Engram table, not a model to pick) | 111 GB, already in all three downloads above | The 4-bit Engram lookup table the model reads from RAM or SSD; all three sets use this one file |"Perplexity" is how surprised the model is by a fixed set of 4,995 test texts; lower is closer to the original. Pick IQ2_XS for coding and agent work when you have the disk. Setup shows all three sizes and warns if your PC is short of disk or RAM. It does not stop you.diff --git a/setup.py b/setup.pyindex 1da4267e3..f919cdb72 100644--- a/setup.py+++ b/setup.py@@ -749,15 +749,15 @@ MULTI_FILE_FAMILIES["deepseek41"]["models"] = {"IST-DAS-2.00bpw": {"label": "IST-DAS 2.00 bpw","about": "the smaller official version: 138 GB of model + 111 GB n-gram table + 8 GB drafter (257 GB of disk). Runs on a PC with "- "a 12 GB card and 40-64 GB of RAM at about 5-7 tokens a second; quality about 16% above the original model's "- "perplexity",+ "a 12 GB card and 40-64 GB of RAM at about 5-7 tokens a second; quality about 15.5% above the original model's "+ "perplexity (code and agent work 5-9%)","ram_gb": 40, "recipe": "ista", "subdir": None, "legacy_subdir": "2.00bpw", "profile": "profile-2.00.bin", "hf": hf(DSV41_ISTA_REPO),"shards": [DSV41_ISTA_SHARD.format(quant="IQ2_XXS", i=i) for i in range(1, 5)],"shared": [DSV41_ISTA_ENGRAM, DSV41_SHARD.format(i=1), DSV41_DSPARK]},"IST-DAS-2.25bpw": {"label": "IST-DAS 2.25 bpw","about": "the better official version: 155 GB of model + 111 GB n-gram table + 8 GB drafter (274 GB of disk, 17 GB more than "- "2.00). About the same speed; quality about 8% above the original model's perplexity (code and agent work 2.5-3.5%)",+ "2.00). About the same speed; quality about 7.3% above the original model's perplexity (code and agent work 2-3%)","ram_gb": 44, "recipe": "ista", "subdir": None, "legacy_subdir": "2.25bpw", "profile": "profile-2.25.bin", "hf": hf(DSV41_ISTA_REPO),"shards": [DSV41_ISTA_SHARD.format(quant="IQ2_XS", i=i) for i in range(1, 5)],"shared": [DSV41_ISTA_ENGRAM, DSV41_SHARD.format(i=1), DSV41_DSPARK]},diff --git a/strata_control/dsv41_fit.py b/strata_control/dsv41_fit.pyindex 1d3d641c6..8de951c2d 100644--- a/strata_control/dsv41_fit.py+++ b/strata_control/dsv41_fit.py@@ -50,7 +50,7 @@ MEASURED = ("4 x Radeon AI PRO R9700 (32 GB) with 251 GB of RAM: prompts of 3,00# The two official IST-DAS sets (ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF, setup.py DSV41_ISTA_FILES): 4 shards each (the experts as IQ1_M / IQ2 / IQ3 types, the# dense weights Q8_0 / Q5_K), plus ONE Engram (110.6 GB, IQ4_NL, shared by both sets, stays on the SSD) and the DSpark drafter (8.0 GB).-# Measured 2026-10-23 (f-dsv41-rel): quality against the original model (ppl +16% for 2.00, +7.7-8.3% for 2.25; code / agent +3.5% / +2.5%+# Measured 2026-10-23 (f-dsv41-rel): quality against the original model (final files, 4,995 positions: ppl +15.5% for 2.00 [code +8.6%, agent +5.3%], +7.3% for 2.25 [code +3.2%, agent +2.2%]# on 2.25); speed on the owner PC (RTX 5070 12 GB, 64 GB RAM, 3.6 GB/s NVMe): answers ~4.7 tokens a second, prompts 121 tokens a second at 4K and# 231 tokens a second at 8K; RTX 3060 12 GB with 46 GB of RAM (the engine held to 36 GB): answers ~7.2 tokens a second on 2.00; 4 x Radeon AI PRO# R9700: answers ~31 tokens a second, prompts 330-373 tokens a second at 8K.@@ -59,8 +59,8 @@ ISTA_DSPARK_BYTES = 7_976_914_240ISTA_META_BYTES = 5_780_589 # the first shard of Unsloth's UD-Q8_K_XL: only the metadata --engram-meta readsISTA_SETS = {"IST-DAS-2.00bpw": {"title": "IST-DAS 2.00 bpw", "set_bytes": 138_238_893_056, "experts_gb": 132.07, "profile": "profile-2.00.bin",- "ppl": "16%", "ram_ok_gb": 40.0, "ram_great_gb": 160.0, "disk_total": 257.0,- "quality": "about 16% above the original model's perplexity (the 2-bit price)"},+ "ppl": "15.5%", "ram_ok_gb": 40.0, "ram_great_gb": 160.0, "disk_total": 257.0,+ "quality": "about 15.5% above the original model's perplexity (code and agent work about 5-9% above)"},# IQ1_M (1.75 bpw): 120,721,120,256 bytes of shards; experts = the shards minus the 6.16 GB of dense weights. RAM class from the experts' size against# the 2.00 set's measured 40 GB (not measured on a computer yet); quality: the H100's 4,995-position score (KL 0.217, ppl 3.80, +21%; code +8.9%, agent +10.2%, English prose +53%)."IST-DAS-1.75bpw": {"title": "IST-DAS 1.75 bpw", "set_bytes": 120_721_120_256, "experts_gb": 114.56, "profile": "profile-2.00.bin",@@ -68,8 +68,8 @@ ISTA_SETS = {"quality": "about 21% above the original model's perplexity: the smallest, fine for code and agent work, noticeably weaker ""on plain prose; pick 2.00 if it fits"},"IST-DAS-2.25bpw": {"title": "IST-DAS 2.25 bpw", "set_bytes": 155_225_824_256, "experts_gb": 149.06, "profile": "profile-2.25.bin",- "ppl": "8%", "ram_ok_gb": 44.0, "ram_great_gb": 176.0, "disk_total": 274.0,- "quality": "about 8% above the original model's perplexity (code and agent work about 2.5-3.5% above), "+ "ppl": "7.3%", "ram_ok_gb": 44.0, "ram_great_gb": 176.0, "disk_total": 274.0,+ "quality": "about 7.3% above the original model's perplexity (code and agent work about 2-3% above), ""the better of the two, 17 GB more disk"},}ISTA_DENSE_GB = 6.16 # the dense weights in the shards (attention, router, shared experts, the head; the embedding stays on the CPU)