Known-issues sheets for local language models Rev 0.1.0 · reviewed every 7 days

Model datasheet · Qwen3.5

Qwen3.5 122B-A10B

The Qwen3.5 that fits: 76GB at 4-bit puts it inside a 96GB machine with room for context, and it gives up surprisingly little to the 397B — 72.0 on SWE-bench against 76.4. The best accuracy-per-gigabyte on this site above 70B.

Vendor
Alibaba
Architecture
MoE · 122B total / ~10B active
Context
262,144 tokens
License
Apache-2.0
Released
2026-02-24
Vision
Yes

→ GGUF (llama.cpp / LM Studio / Ollama)

§1 Characteristics by quantization band

Q2–Q3 — 2–3 bit

56.4GB weights · e.g. Q3_K_M + KV: 192MB at 8K · 768MB at 32K · 3GB at 128K
Coding 5/10
data checked Aug 2026
  • quant-degradation-community — editorial band derivation @ Q3_K_M · aggregated · 2026-08-31

    Editorial derivation: two points down. At 3-bit a sparse MoE loses expert-routing precision first, which surfaces as dropped tool arguments and broken multi-file edits before prose visibly suffers.

Tool calling / agentic 4/10
data checked Aug 2026
  • quant-degradation-community — editorial band derivation @ Q3_K_M · aggregated · 2026-08-31

    Editorial derivation: two points down. At 3-bit a sparse MoE loses expert-routing precision first, which surfaces as dropped tool arguments and broken multi-file edits before prose visibly suffers.

Q4–Q5 — 4–5 bit

76.5GB weights · e.g. Q4_K_M + KV: 192MB at 8K · 768MB at 32K · 3GB at 128K
Coding 7/10
data checked Aug 2026
  • quant-degradation-community — editorial band derivation @ Q4_K_M · aggregated · 2026-08-31

    Editorial derivation: one point down from the measured bf16 figure. 4-bit is the band a model this size is actually run at, and the loss is real but modest.

Tool calling / agentic 7/10
data checked Aug 2026
  • quant-degradation-community — editorial band derivation @ Q4_K_M · aggregated · 2026-08-31

    Editorial derivation: one point down from the measured bf16 figure. 4-bit is the band a model this size is actually run at, and the loss is real but modest.

Q6–Q8 — 6–8 bit

101GB weights · e.g. Q6_K + KV: 192MB at 8K · 768MB at 32K · 3GB at 128K
Coding 8/10
data checked Aug 2026
  • quant-degradation-community — editorial band derivation @ Q6_K · aggregated · 2026-08-31

    Editorial derivation: no drop from the measured bf16 figure. 6-8 bit is effectively lossless on a model this size — the differences that show up at 4-bit and below are not measurable here. Recorded explicitly rather than left to band fallback, which would otherwise borrow the 4-bit number and subtract a point.

Factuality 8/10
data checked Aug 2026
  • quant-degradation-community — editorial band derivation @ Q6_K · aggregated · 2026-08-31

    Editorial derivation: no drop from the measured bf16 figure. 6-8 bit is effectively lossless on a model this size — the differences that show up at 4-bit and below are not measurable here. Recorded explicitly rather than left to band fallback, which would otherwise borrow the 4-bit number and subtract a point.

Instruction following 9/10
data checked Aug 2026
  • quant-degradation-community — editorial band derivation @ Q6_K · aggregated · 2026-08-31

    Editorial derivation: no drop from the measured bf16 figure. 6-8 bit is effectively lossless on a model this size — the differences that show up at 4-bit and below are not measurable here. Recorded explicitly rather than left to band fallback, which would otherwise borrow the 4-bit number and subtract a point.

Math & reasoning 8/10
data checked Aug 2026
  • quant-degradation-community — editorial band derivation @ Q6_K · aggregated · 2026-08-31

    Editorial derivation: no drop from the measured bf16 figure. 6-8 bit is effectively lossless on a model this size — the differences that show up at 4-bit and below are not measurable here. Recorded explicitly rather than left to band fallback, which would otherwise borrow the 4-bit number and subtract a point.

Tool calling / agentic 8/10
data checked Aug 2026
  • quant-degradation-community — editorial band derivation @ Q6_K · aggregated · 2026-08-31

    Editorial derivation: no drop from the measured bf16 figure. 6-8 bit is effectively lossless on a model this size — the differences that show up at 4-bit and below are not measurable here. Recorded explicitly rather than left to band fallback, which would otherwise borrow the 4-bit number and subtract a point.

FP16 — full precision (fp16/bf16)

244GB weights · e.g. bf16 + KV: 192MB at 8K · 768MB at 32K · 3GB at 128K
Coding 8/10
data checked Aug 2026
  • vendor-model-cardSWE-bench Verified = 72 @ bf16 · vendor-reported · 2026-08-31

    LiveCodeBench v6 78.9, Terminal Bench 2 49.4. Within 4.4 points of the 397B at less than a third of the weights.

Factuality 8/10
data checked Aug 2026
  • vendor-model-cardMMLU-Pro = 86.7 @ bf16 · vendor-reported · 2026-08-31

    Knowledge benchmark only; no hallucination-rate figure is published for this model.

Instruction following 9/10
data checked Aug 2026
  • vendor-model-cardIFEval = 93.4 @ bf16 · vendor-reported · 2026-08-31

    IFBench 76.1. The highest IFEval figure in this catalogue — above the 397B's 92.6 and Llama 3.3 70B's 92.1.

Math & reasoning 8/10
data checked Aug 2026
Tool calling / agentic 8/10
data checked Aug 2026
  • vendor-model-cardBFCL-V4 = 72.2 @ bf16 · vendor-reported · 2026-08-31

    Terminal Bench 2 49.4 — essentially level with the 397B's 72.9 on BFCL.

§2 Known issues & what fixes them

ISSUE-01 moderate Q2–Q3 · tool-calling, coding

3-bit is where the agentic behaviour goes. With 10B active parameters spread over 256 experts, routing decisions are made on a small slice of the model, and 3-bit quantization blurs exactly that slice — malformed tool arguments and dropped call sequences show up well before the prose reads worse.

Fix
Move up a quant band [strong]

The 76.5GB 4-bit build is the one to run; it fits a 96GB machine with context to spare, which is the whole argument for this model over the 397B.

Fix
MCP / external tools [partial]

Grammar-constrained tool schemas recover much of the malformed-argument loss.

Evidence · 2 sources · community-consensus
ISSUE-02 moderate Q2–Q3 / Q4–Q5 / Q6–Q8 / FP16 · coding, math

Every score here is Alibaba's own, published on release day and not independently replicated in this dataset. The claim that a 122B model lands within a few points of a 397B one is the interesting part and the part most in need of outside confirmation. Long-context and factuality cells are blank rather than estimated — no RULER or hallucination result exists for it.

No fix
No known fix — choose a different model

A caveat on the evidence, not on the model.

Evidence · 2 sources · community-consensus