diff --git a/common/.config/aichat/config.yaml b/common/.config/aichat/config.yaml index f3c29df..08dc77f 100644 --- a/common/.config/aichat/config.yaml +++ b/common/.config/aichat/config.yaml @@ -48,6 +48,11 @@ clients: supports_vision: true - name: GLM-4.7-Flash-UD-Q4_K_XL max_input_tokens: 22000 # ctx 24576 · ~21 t/s — quality coder + - name: GLM-4.7-Flash-UD-Q3_K_XL + max_input_tokens: 22000 # ctx 24576 · ~28 t/s — fast coder (3-bit) + - name: Ornith-1.5-35B-A3B-IQ3_XXS + max_input_tokens: 22000 # ctx 24576 · ~32 t/s — agentic coder, thinking + supports_vision: true - name: gpt-oss-20b max_input_tokens: 62000 # ctx 65536 · ~38 t/s — fast reasoning + tools - name: gpt-oss-20b-low diff --git a/common/.config/misc/tuis.txt b/common/.config/misc/tuis.txt index 7c5b933..822c4c0 100644 --- a/common/.config/misc/tuis.txt +++ b/common/.config/misc/tuis.txt @@ -12,6 +12,7 @@ btop bandwhich mtr gping +flow bmon profanity nmtui diff --git a/common/.config/opencode/opencode.json b/common/.config/opencode/opencode.json index 3b47917..c3039f4 100644 --- a/common/.config/opencode/opencode.json +++ b/common/.config/opencode/opencode.json @@ -150,6 +150,8 @@ "gemma-4-26B-A4B-it-UD-IQ4_XS": { "name": "Gemma 4 26B · 24k · vision — quality generalist (~34 t/s, remote)", "attachment": true, "limit": { "context": 24576, "output": 4096 } }, "gemma-4-E4B-it-UD-Q8_K_XL": { "name": "Gemma 4 E4B · 64k · vision — fast generalist, long docs (~57 t/s, remote)", "attachment": true, "limit": { "context": 65536, "output": 16384 } }, "GLM-4.7-Flash-UD-Q4_K_XL": { "reasoning": true, "interleaved": "reasoning_content", "name": "GLM-4.7 Flash · 24k — quality coder (~21 t/s, remote)", "limit": { "context": 24576, "output": 8192 } }, + "GLM-4.7-Flash-UD-Q3_K_XL": { "reasoning": true, "interleaved": "reasoning_content", "name": "GLM-4.7 Flash Q3 · 24k — fast coder (~28 t/s, remote)", "limit": { "context": 24576, "output": 8192 } }, + "Ornith-1.5-35B-A3B-IQ3_XXS": { "reasoning": true, "name": "Ornith 1.5 35B · 24k · vision — agentic coder, thinking (~32 t/s, remote)", "attachment": true, "limit": { "context": 24576, "output": 8192 } }, "gpt-oss-20b": { "reasoning": true, "name": "gpt-oss 20B · 64k — fast reasoning + tools (~38 t/s, remote)", "limit": { "context": 65536, "output": 8192 } }, "gpt-oss-20b-low": { "reasoning": true, "name": "gpt-oss 20B low · 64k — snappy answers (~37 t/s, remote)", "limit": { "context": 65536, "output": 8192 } } } @@ -171,6 +173,8 @@ "gemma-4-26B-A4B-it-UD-IQ4_XS": { "name": "Gemma 4 26B · 24k · vision — quality generalist (~34 t/s)", "attachment": true, "limit": { "context": 24576, "output": 4096 } }, "gemma-4-E4B-it-UD-Q8_K_XL": { "name": "Gemma 4 E4B · 64k · vision — fast generalist, long docs (~57 t/s)", "attachment": true, "limit": { "context": 65536, "output": 16384 } }, "GLM-4.7-Flash-UD-Q4_K_XL": { "reasoning": true, "interleaved": "reasoning_content", "name": "GLM-4.7 Flash · 24k — quality coder (~21 t/s)", "limit": { "context": 24576, "output": 8192 } }, + "GLM-4.7-Flash-UD-Q3_K_XL": { "reasoning": true, "interleaved": "reasoning_content", "name": "GLM-4.7 Flash Q3 · 24k — fast coder (~28 t/s)", "limit": { "context": 24576, "output": 8192 } }, + "Ornith-1.5-35B-A3B-IQ3_XXS": { "reasoning": true, "name": "Ornith 1.5 35B · 24k · vision — agentic coder, thinking (~32 t/s)", "attachment": true, "limit": { "context": 24576, "output": 8192 } }, "gpt-oss-20b": { "reasoning": true, "name": "gpt-oss 20B · 64k — fast reasoning + tools (~38 t/s)", "limit": { "context": 65536, "output": 8192 } }, "gpt-oss-20b-low": { "reasoning": true, "name": "gpt-oss 20B low · 64k — snappy answers (~37 t/s)", "limit": { "context": 65536, "output": 8192 } } } diff --git a/common/.pi/agent/models.json b/common/.pi/agent/models.json index 7558ea8..6819163 100644 --- a/common/.pi/agent/models.json +++ b/common/.pi/agent/models.json @@ -95,6 +95,26 @@ "maxTokens": 4096, "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 } }, + { + "id": "GLM-4.7-Flash-UD-Q3_K_XL", + "name": "GLM-4.7 Flash Q3 · 24k — fast coder (~28 t/s)", + "reasoning": true, + "compat": { "thinkingFormat": "qwen-chat-template" }, + "input": ["text"], + "contextWindow": 24576, + "maxTokens": 4096, + "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 } + }, + { + "id": "Ornith-1.5-35B-A3B-IQ3_XXS", + "name": "Ornith 1.5 35B · 24k · vision — agentic coder, thinking (~32 t/s)", + "reasoning": true, + "compat": { "thinkingFormat": "qwen-chat-template" }, + "input": ["text", "image"], + "contextWindow": 24576, + "maxTokens": 4096, + "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 } + }, { "id": "gpt-oss-20b", "name": "gpt-oss 20B · 64k — fast reasoning + tools (~38 t/s)", @@ -210,6 +230,26 @@ "maxTokens": 4096, "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 } }, + { + "id": "GLM-4.7-Flash-UD-Q3_K_XL", + "name": "GLM-4.7 Flash Q3 · 24k — fast coder (~28 t/s)", + "reasoning": true, + "compat": { "thinkingFormat": "qwen-chat-template" }, + "input": ["text"], + "contextWindow": 24576, + "maxTokens": 4096, + "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 } + }, + { + "id": "Ornith-1.5-35B-A3B-IQ3_XXS", + "name": "Ornith 1.5 35B · 24k · vision — agentic coder, thinking (~32 t/s)", + "reasoning": true, + "compat": { "thinkingFormat": "qwen-chat-template" }, + "input": ["text", "image"], + "contextWindow": 24576, + "maxTokens": 4096, + "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 } + }, { "id": "gpt-oss-20b", "name": "gpt-oss 20B · 64k — fast reasoning + tools (~38 t/s)", diff --git a/fl/.config/kglobalshortcutsrc b/fl/.config/kglobalshortcutsrc index 3971edf..83d32ae 100644 --- a/fl/.config/kglobalshortcutsrc +++ b/fl/.config/kglobalshortcutsrc @@ -316,9 +316,6 @@ _launch=Meta+C [services][org.gajim.Gajim.desktop] StartChat=Meta+G -[services][org.kde.dolphin.desktop] -_launch=Meta+E - [services][org.kde.krunner.desktop] _launch=Search\tAlt+Space\tAlt+F2\tCtrl+Alt+S\tMeta+A\tMeta+S diff --git a/fl/.config/llamacpp/README.md b/fl/.config/llamacpp/README.md index 909495d..ed36ec0 100644 --- a/fl/.config/llamacpp/README.md +++ b/fl/.config/llamacpp/README.md @@ -60,9 +60,11 @@ starves the desktop and freezes the PC (reboot). Hard-won rules: | `Qwen3.5-9B-UD-Q6_K_XL` | 32.1 | 32k | vision, MTP, reasoning | small Qwen, quick tasks | | `Qwen3-Coder-30B-Instruct-UD-Q3_K_XL` | **~30** clean / 27.0 evening @moe12 | 32k | — | **main agent coder** — won the 2026-08-06 quant race; moe12 verified evening 08-07 + clean 08-08 | | `GLM-4.7-Flash-UD-Q4_K_XL` | **21.5** @moe22 | 24k | reasoning | quality coder (opencode subagents); KV fix + moe22 ✓ verified clean 08-08 | +| `GLM-4.7-Flash-UD-Q3_K_XL` | **26.0** @moe12 (2.0 daytime baseline; ~28 clean) | 24k | reasoning | **fast coder** — re-added 09-21 because Q4's 21.5 dragged in agent loops; 3-bit, evening-safe at moe12 (13.4 used / 3.8 free @2.0); Q4 stays for hard reviews | | `Qwen3-Coder-Next-UD-IQ3_XXS` | 16.0 | **128k** | 80B-A3B | long-session coder (128k ctx) | | `Qwen3.8-27B-UD-IQ3_XXS` | 14.5 (10.9 w/o MTP) | 24k | vision, MTP, hybrid reasoner | ⚠ **clean-desktop specialty** (kept 09-10 over the ≥22 gate) — dense-27B quality, slow: its Gated-DeltaNet layers are Vulkan-bound (prefill ~30). 2.5 GB free @1.6 baseline @24k (✓ 09-10); **never on a busy evening desktop** (~1 GB free = GTT freeze) | | `Qwen3-Embedding-0.6B` | 33 (CPU) | 8k | CPU-only, `/v1/embeddings` | RAG/search embedder (not a chat model) | +| `Ornith-1.5-35B-A3B-IQ3_XXS` | **32.1** @moe16 | 24k | MTP, vision, thinking | **agentic coder** (added 09-21) — Qwen3.5-MoE derivative claiming +15 Terminal-Bench / +5.6 SWE-bench over Qwen3.6-35B; the only coder with MTP; 13.8 used / 3.3 free @2.0 | Expected run-to-run spread: MTP models swing ±15% with draft **acceptance rate** (content- dependent); CPU-heavy presets (Coder-Next, embedder) dip under daytime CPU contention. @@ -72,6 +74,11 @@ Treat clean night runs as the reference; don't retune on daytime deltas. - **Agent coding loops** (edit/test cycles): `Qwen3-Coder-30B` — best speed/quality balance at 32k. - **Hard code, reviews, tricky bugs**: `GLM-4.7-Flash` — strongest 30B-class coder, slightly slower. +- **GLM at agent-loop speed**: `GLM-4.7-Flash-UD-Q3_K_XL` — same model, 3-bit, ~28 t/s; pick it + when the Q4's 21 t/s drags, keep Q4 for the review that has to be right. +- **Agentic coding with reasoning** (⚗ new, judge over the next weeks): `Ornith-1.5-35B-A3B` — + Qwen3.5-MoE derivative, 32 t/s *with* MTP and a thinking preamble (~4 s TTFT), vision. If its + launch numbers hold in practice it displaces GLM/Coder-30B for agent loops. - **Marathon sessions / huge conversation history**: `Qwen3-Coder-Next` — 128k ctx at only 6 GB VRAM (hybrid attention). Caveat: ~33 t/s prefill means it's for *growing* sessions (`cache-reuse` makes turns incremental), **not** for cold-dumping 100k tokens. @@ -131,6 +138,8 @@ the router, but chats/presets saved against the old id need re-picking. 2026-08-16: `Qwen3.8-27B-UD-IQ3_XXS` (⚗ candidate) added to all six client files. 2026-09-10: kept as ⚠ clean-desktop specialty after the gate bench finally ran on the v3 gguf (14.5 t/s MTP / 10.9 base, 2.8 GB free @1.5); server ctx restored to 24576 = client ctx, no client edits. +2026-09-21: `GLM-4.7-Flash-UD-Q3_K_XL` (⚡ fast coder) added to all six client files next to the Q4. +2026-09-21: `Ornith-1.5-35B-A3B-IQ3_XXS` (agentic coder, thinking + vision) added to all six client files after passing its gate (32.1 t/s @moe16). ## Tuning cheat-sheet diff --git a/fl/.config/llamacpp/config.ini b/fl/.config/llamacpp/config.ini index 5a22169..57121da 100644 --- a/fl/.config/llamacpp/config.ini +++ b/fl/.config/llamacpp/config.ini @@ -455,14 +455,73 @@ top-p = 0.95 top-k = 64 sleep-idle-seconds = 30 +# ───────────────────────────────────────────────────────────────────────────── +# Ornith (Qwen3.5-MoE derivative) +# ───────────────────────────────────────────────────────────────────────────── + +[Ornith-1.5-35B-A3B-IQ3_XXS] +# ✓ KEPT 2026-09-21 (gate passed: 32.1 t/s MTP, 13.8 used / 3.3 free @moe16) — Ornith-1.5-35B-A3B (ornith-ai / DeepReinforce, MIT, +# released ~2026-08-24): Qwen3.5-MoE architecture (qwen35moe: 40 layers, hybrid GDN 3:1, 256 +# experts / 8 active + shared, ~3B active, vision, n_ctx_train 262144), continued-pretrained and +# RL'd with a self-improvement loop. Card claims it beats Qwen3.6-35B-A3B on every coding/agentic +# bench (Terminal-Bench 2.1 67.8 vs 52.5, SWE-bench Verified 79 vs 73.4). Same shape as the daily +# driver → same recipe: MTP draft + experts on CPU. Role if it passes: AGENTIC CODER (the only +# coder here with MTP — Coder-30B 30 t/s and GLM Q3 26 t/s have none) and/or daily driver. +# MTP head VERIFIED in the gguf header 09-21 (nextn_predict_layers = 1, block_count 41 = 40+1) — +# present in bartowski's plain quants and the official Q4_K_M alike; no "-MTP" repo needed. +# Thinking is ON by default ( block; card sampling 0.6/0.95/20). Kept ON for the coder +# role; an instruct alias = same file + `reasoning-budget = 0` exactly like the daily driver. +# VRAM: file is +1.27 GB vs the daily driver's 14.07 → start at moe20 (≈ Qwen@moe16 footprint: +# predicted ~13.9 used / ~3.3 free @2.0 baseline). Until downloaded, sweep with `-x` this id. +# GATE: MTP decode ≥ ~30 t/s AND free ≥ 2.5 → keep; step moe 20→16 while free ≥ 2.5; then wire +# the six client files + README row. Anything less → retire + delete (the Qwen stays). +# ✓ LOADED + BENCHED 2026-09-21 17:31 @moe20 (2.0 baseline): 27.9 t/s / 52 pp / 12.4 used / 4.8 +# free → footprint only 10.4 GB (predicted 11.9). MTP draft active (spec column). Speed gate +# not met yet but 2.3 GB of headroom is unused → step moe 20→16 (= daily driver; the Qwen went +# 19.8→35.9 t/s over moe 24→16). Predicted @moe16: ~13.8 used / ~3.4 free @2.0. +# ✓ GATE PASSED 17:34 @moe16 (2.0 baseline): 32.1 t/s / 74 pp / TTFT 3.9 s (thinking preamble) / +# 13.8 used / 3.3 free — prediction exact. Both gate halves met → wired into the six client +# files + README 09-21. KEEP moe16 (= daily-driver envelope; moe14 ≈ +1-2 t/s for the last +# 0.8 GB of margin — not on an evening box). Draft acceptance not recorded yet (grep the log). +# Role: agentic coder with reasoning — the only coder here with MTP (Coder-30B 30, GLM Q3 26). +# Instruct alias (reasoning-budget = 0, same file) still optional — add if agent loops want +# the ~4 s thinking TTFT gone. +# ⬇ DOWNLOAD from bartowski/Ornith-1.5-35B-A3B-GGUF (imatrix; the official repo has only Q4_K_M+ +# ≥ 21.7 GB, unsloth has no 1.5 quants yet): +# Ornith-1.5-35B-A3B-IQ3_XXS.gguf 15,340,447,392 B · sha256 8918ccb9ee29abe3875efec0c3e86f0e35ef0b8a03e3f0e1c422869859a518d0 +# mmproj-Ornith-1.5-35B-A3B-f16.gguf 899,283,296 B · sha256 815c9a671991aceeef46ca1aa103b64499db8cfadf21c83005a20ed839d53c7c +model = /home/anon/software/models/Ornith-1.5-35B-A3B-IQ3_XXS.gguf +mmproj = /home/anon/software/models/mmproj-Ornith-1.5-35B-A3B-f16.gguf +spec-type = draft-mtp +spec-draft-n-max = 2 +ctx-size = 24576 # = the daily driver; n_ctx_train 262144 — raise only after a bench +n-gpu-layers = 99 +n-cpu-moe = 16 # ✓ KEEP (09-21: 32.1 t/s, 13.8 used / 3.3 free @2.0; moe20 was 27.9 / + # 12.4 / 4.8). = daily-driver envelope; moe14 not worth the margin. +threads = 6 +flash-attn = on +cache-type-k = q8_0 +cache-type-v = q4_0 # mixed KV is fine on this arch (daily driver runs the same) +batch-size = 2048 +ubatch-size = 512 +cache-reuse = 256 # inert under mmproj ("not supported by multimodal") — kept for parity +defrag-thold = 0.1 +temp = 0.6 # model card, general use: 0.6 / 0.95 / 20 (1.0 only for bench reproduction) +top-p = 0.95 +top-k = 20 +min-p = 0 +jinja = on +sleep-idle-seconds = 120 + # ───────────────────────────────────────────────────────────────────────────── # GLM # ───────────────────────────────────────────────────────────────────────────── [GLM-4.7-Flash-UD-Q4_K_XL] -# 30B-A3B MoE, primary coder. Upgraded UD-Q3_K_XL (~14 GB) → UD-Q4_K_XL (17.5 GB, unsloth's -# recommended quant) 2026-07-16, benched clean same day → the old GLM-4.7-Flash-UD-Q3_K_XL.gguf -# can be deleted. +# 30B-A3B MoE, QUALITY coder. Upgraded UD-Q3_K_XL (~14 GB) → UD-Q4_K_XL (17.5 GB, unsloth's +# recommended quant) 2026-07-16, benched clean same day. 2026-09-21: the Q3 quant is BACK as the +# separate fast-coder preset [GLM-4.7-Flash-UD-Q3_K_XL] below (21.5 t/s here was too slow for +# daily agent use) — keep BOTH files; this one stays for hard reviews. # Tuning trajectory: Q3@moe9 = 28.2 t/s → Q4@moe24 = 17.9 (measured 2026-07-16) → now moe18, # lower stepwise toward 16 while bench keeps free ≥2.5 GB. model = /home/anon/software/models/GLM-4.7-Flash-UD-Q4_K_XL.gguf @@ -508,6 +567,48 @@ reasoning-preserve = true # ⚗ option ACCEPTED by the build (loaded + ra # next days; remove if reasoning bleed ever pollutes final answers. sleep-idle-seconds = 60 +[GLM-4.7-Flash-UD-Q3_K_XL] +# ⚡ FAST CODER — same GLM-4.7-Flash, 3-bit. RE-ADDED 2026-09-21: the user found the Q4 preset's +# 21.5 t/s (22 expert layers in RAM) too slow for agent loops; this quant fit far more of the +# experts on the GPU and was the fastest coder this box ever ran. HISTORY (07-16, pre-KV-fix +# era): Q3@moe9 = 28.2-29.7 t/s, @moe12 = 28.1, @moe24 = 18.9 (9.5 used / 7.6 free @16k). +# Quality: UD 3-bit — "coders want ≥4-bit" (README) is why Q4 exists; pick Q3 for speed, Q4 for +# hard reviews. Same deepseek2/MLA arch → same-type KV (q8/q8) is mandatory here too. +# GATE: keep if bench ≥ ~27 t/s AND free ≥ 2.5 GB @ a ≤1.9 baseline. Start at moe12 (safe), +# step to moe9 if free allows (~+0.75 GB per 3 layers on GPU, +~1 t/s). +# ✓ BENCHED 2026-09-21 16:29 (2.0 DAYTIME baseline): 26.0 t/s / 46 pp / 13.4 used / 3.8 free → +# footprint 11.4 GB. Speed = July's 28.1 minus the usual busy-desktop tax (clean-night +# reference still to record); VRAM passes with room. +21% over the Q4's 21.5. +# Re-run 16:34 (2.1 baseline): 25.9 t/s / 65 pp / 13.5 used / 3.7 free — reproducible; the +# first run's 46 pp was CPU contention (prefill now matches the Q4's ~60). +# DECISION: KEEP moe12, do NOT step to moe9. This preset's job is EVENING agent loops, so the +# evening envelope rules: 11.4 + 3.3 evening baseline = 14.7 used / 2.5 free = exactly the +# target; moe9 would be ~15.4 used on a busy evening = the coder's old death zone, for ~+1 t/s. +# Want more speed on a QUIET desktop? A same-file alias at moe6 (~+1.5 GB, maybe ~29-30) is the +# gpt-oss-low pattern — not added; ask. +# ⬇ DOWNLOAD unsloth/GLM-4.7-Flash-GGUF (repo unchanged since 2026-02-12): +# GLM-4.7-Flash-UD-Q3_K_XL.gguf — 13,782,004,064 B (13.78 GB) +# sha256 582728c0f6931a1cf734d5a7cf60ec73522fb79811e004cbc12476dd69b033bf +model = /home/anon/software/models/GLM-4.7-Flash-UD-Q3_K_XL.gguf +ctx-size = 24576 # = clients (MLA KV is compact; n_ctx_train 202752) +n-gpu-layers = 99 +n-cpu-moe = 12 # ✓ KEEP (09-21: 26.0 t/s, 13.4 used / 3.8 free @2.0 daytime). Evening- + # safe (~14.7 used @3.3). moe9 = +~1 t/s for ~15.4 evening → no. +threads = 6 +flash-attn = on +cache-type-k = q8_0 +cache-type-v = q8_0 # MLA: mixed K/V types are rejected at context creation (see Q4 preset) +batch-size = 2048 +ubatch-size = 512 +cache-reuse = 256 +defrag-thold = 0.1 +temp = 0.6 # mirrors the Q4 preset (unsloth: 0.7/top-p 1.0 tools, 1.0/0.95 general) +top-p = 0.95 +min-p = 0.01 +jinja = on +reasoning-preserve = true # mirrors the Q4 preset — same behaviour flag, same review caveat +sleep-idle-seconds = 60 + # ───────────────────────────────────────────────────────────────────────────── # Utility & candidates # ───────────────────────────────────────────────────────────────────────────── diff --git a/lw/.config/aichat/config.yaml b/lw/.config/aichat/config.yaml index 9c41d57..a7a91c9 100644 --- a/lw/.config/aichat/config.yaml +++ b/lw/.config/aichat/config.yaml @@ -73,6 +73,11 @@ clients: supports_vision: true - name: GLM-4.7-Flash-UD-Q4_K_XL max_input_tokens: 22000 # ctx 24576 · ~21 t/s — quality coder + - name: GLM-4.7-Flash-UD-Q3_K_XL + max_input_tokens: 22000 # ctx 24576 · ~28 t/s — fast coder (3-bit) + - name: Ornith-1.5-35B-A3B-IQ3_XXS + max_input_tokens: 22000 # ctx 24576 · ~32 t/s — agentic coder, thinking + supports_vision: true - name: gpt-oss-20b max_input_tokens: 62000 # ctx 65536 · ~38 t/s — fast reasoning + tools - name: gpt-oss-20b-low diff --git a/lw/.config/opencode/opencode.json b/lw/.config/opencode/opencode.json index 917479d..c511b98 100644 --- a/lw/.config/opencode/opencode.json +++ b/lw/.config/opencode/opencode.json @@ -168,6 +168,8 @@ "gemma-4-26B-A4B-it-UD-IQ4_XS": { "name": "Gemma 4 26B · 24k · vision — quality generalist (~34 t/s, remote)", "attachment": true, "limit": { "context": 24576, "output": 4096 } }, "gemma-4-E4B-it-UD-Q8_K_XL": { "name": "Gemma 4 E4B · 64k · vision — fast generalist, long docs (~57 t/s, remote)", "attachment": true, "limit": { "context": 65536, "output": 16384 } }, "GLM-4.7-Flash-UD-Q4_K_XL": { "reasoning": true, "interleaved": "reasoning_content", "name": "GLM-4.7 Flash · 24k — quality coder (~21 t/s, remote)", "limit": { "context": 24576, "output": 8192 } }, + "GLM-4.7-Flash-UD-Q3_K_XL": { "reasoning": true, "interleaved": "reasoning_content", "name": "GLM-4.7 Flash Q3 · 24k — fast coder (~28 t/s, remote)", "limit": { "context": 24576, "output": 8192 } }, + "Ornith-1.5-35B-A3B-IQ3_XXS": { "reasoning": true, "name": "Ornith 1.5 35B · 24k · vision — agentic coder, thinking (~32 t/s, remote)", "attachment": true, "limit": { "context": 24576, "output": 8192 } }, "gpt-oss-20b": { "reasoning": true, "name": "gpt-oss 20B · 64k — fast reasoning + tools (~38 t/s, remote)", "limit": { "context": 65536, "output": 8192 } }, "gpt-oss-20b-low": { "reasoning": true, "name": "gpt-oss 20B low · 64k — snappy answers (~37 t/s, remote)", "limit": { "context": 65536, "output": 8192 } } } @@ -189,6 +191,8 @@ "gemma-4-26B-A4B-it-UD-IQ4_XS": { "name": "Gemma 4 26B · 24k · vision — quality generalist (~34 t/s)", "attachment": true, "limit": { "context": 24576, "output": 4096 } }, "gemma-4-E4B-it-UD-Q8_K_XL": { "name": "Gemma 4 E4B · 64k · vision — fast generalist, long docs (~57 t/s)", "attachment": true, "limit": { "context": 65536, "output": 16384 } }, "GLM-4.7-Flash-UD-Q4_K_XL": { "reasoning": true, "interleaved": "reasoning_content", "name": "GLM-4.7 Flash · 24k — quality coder (~21 t/s)", "limit": { "context": 24576, "output": 8192 } }, + "GLM-4.7-Flash-UD-Q3_K_XL": { "reasoning": true, "interleaved": "reasoning_content", "name": "GLM-4.7 Flash Q3 · 24k — fast coder (~28 t/s)", "limit": { "context": 24576, "output": 8192 } }, + "Ornith-1.5-35B-A3B-IQ3_XXS": { "reasoning": true, "name": "Ornith 1.5 35B · 24k · vision — agentic coder, thinking (~32 t/s)", "attachment": true, "limit": { "context": 24576, "output": 8192 } }, "gpt-oss-20b": { "reasoning": true, "name": "gpt-oss 20B · 64k — fast reasoning + tools (~38 t/s)", "limit": { "context": 65536, "output": 8192 } }, "gpt-oss-20b-low": { "reasoning": true, "name": "gpt-oss 20B low · 64k — snappy answers (~37 t/s)", "limit": { "context": 65536, "output": 8192 } } } diff --git a/lw/.pi/agent/models.json b/lw/.pi/agent/models.json index f0a1de4..3c287e8 100644 --- a/lw/.pi/agent/models.json +++ b/lw/.pi/agent/models.json @@ -180,6 +180,26 @@ "maxTokens": 2048, "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 } }, + { + "id": "GLM-4.7-Flash-UD-Q3_K_XL", + "name": "GLM-4.7 Flash Q3 · 24k — fast coder (~28 t/s)", + "reasoning": true, + "compat": { "thinkingFormat": "qwen-chat-template" }, + "input": ["text"], + "contextWindow": 24576, + "maxTokens": 2048, + "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 } + }, + { + "id": "Ornith-1.5-35B-A3B-IQ3_XXS", + "name": "Ornith 1.5 35B · 24k · vision — agentic coder, thinking (~32 t/s)", + "reasoning": true, + "compat": { "thinkingFormat": "qwen-chat-template" }, + "input": ["text", "image"], + "contextWindow": 24576, + "maxTokens": 2048, + "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 } + }, { "id": "gpt-oss-20b", "name": "gpt-oss 20B · 64k — fast reasoning + tools (~38 t/s)", @@ -295,6 +315,26 @@ "maxTokens": 2048, "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 } }, + { + "id": "GLM-4.7-Flash-UD-Q3_K_XL", + "name": "GLM-4.7 Flash Q3 · 24k — fast coder (~28 t/s)", + "reasoning": true, + "compat": { "thinkingFormat": "qwen-chat-template" }, + "input": ["text"], + "contextWindow": 24576, + "maxTokens": 2048, + "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 } + }, + { + "id": "Ornith-1.5-35B-A3B-IQ3_XXS", + "name": "Ornith 1.5 35B · 24k · vision — agentic coder, thinking (~32 t/s)", + "reasoning": true, + "compat": { "thinkingFormat": "qwen-chat-template" }, + "input": ["text", "image"], + "contextWindow": 24576, + "maxTokens": 2048, + "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 } + }, { "id": "gpt-oss-20b", "name": "gpt-oss 20B · 64k — fast reasoning + tools (~38 t/s)", diff --git a/lw/.pi/agent/settings.json b/lw/.pi/agent/settings.json index 14de621..d923aee 100644 --- a/lw/.pi/agent/settings.json +++ b/lw/.pi/agent/settings.json @@ -59,8 +59,9 @@ "ex": "mode" } }, - "lastChangelogVersion": "0.83.0", + "lastChangelogVersion": "0.85.1", "packages": [ "npm:pi-vim" - ] + ], + "hideThinkingBlock": false } \ No newline at end of file